├── .gitattributes
├── .github
    ├── pull_request_template.md
    └── workflows
    │   └── maven.yml
├── .gitignore
├── .mvn
    └── wrapper
    │   ├── maven-wrapper.jar
    │   └── maven-wrapper.properties
├── 1brc.png
├── LICENSE.txt
├── README.md
├── additional_build_step_thomaswue.sh
├── calculate_average_Edgar-P-Yan.sh
├── calculate_average_baseline.sh
├── cleanup.sh
├── create_measurements.sh
├── create_measurements2.sh
├── create_measurements3.sh
├── data
    └── weather_stations.csv
├── etc
    ├── eclipse-formatter-config.xml
    └── license.txt
├── eval.sh
├── evaluate.sh
├── mvnw
├── mvnw.cmd
├── pom.xml
├── prepare.sh
├── process.sh
├── process_output.java
├── src
    ├── main
    │   ├── java
    │   │   ├── dev
    │   │   │   └── morling
    │   │   │   │   └── onebrc
    │   │   │   │       ├── CalculateAverage.java
    │   │   │   │       ├── CreateMeasurements.java
    │   │   │   │       ├── CreateMeasurements2.java
    │   │   │   │       └── CreateMeasurements3.java
    │   │   └── org
    │   │   │   └── rschwietzke
    │   │   │       ├── CheaperCharBuffer.java
    │   │   │       └── FastRandom.java
    │   ├── nodejs
    │   │   ├── Edgar-P-yan
    │   │   │   ├── .gitignore
    │   │   │   ├── README.md
    │   │   │   ├── index.js
    │   │   │   ├── package-lock.json
    │   │   │   ├── package.json
    │   │   │   ├── result.txt
    │   │   │   └── tsconfig.json
    │   │   └── baseline
    │   │   │   ├── .gitignore
    │   │   │   ├── index.js
    │   │   │   ├── package-lock.json
    │   │   │   ├── package.json
    │   │   │   └── tsconfig.json
    │   └── resources
    │   │   └── .dontdelete
    └── test
    │   └── resources
    │       ├── .dontdelete
    │       └── samples
    │           ├── measurements-1.out
    │           ├── measurements-1.txt
    │           ├── measurements-10.out
    │           ├── measurements-10.txt
    │           ├── measurements-10000-unique-keys.out
    │           ├── measurements-10000-unique-keys.txt
    │           ├── measurements-2.out
    │           ├── measurements-2.txt
    │           ├── measurements-20.out
    │           ├── measurements-20.txt
    │           ├── measurements-3.out
    │           ├── measurements-3.txt
    │           ├── measurements-boundaries.out
    │           ├── measurements-boundaries.txt
    │           ├── measurements-complex-utf8.out
    │           └── measurements-complex-utf8.txt
├── test.sh
├── test_all.sh
└── tocsv.sh


/.gitattributes:
--------------------------------------------------------------------------------
 1 | *.java          text
 2 | *.md            text
 3 | *.yml           text
 4 | *.xml           text
 5 | *.gradle        text
 6 | *.properties    text
 7 | mvnw            text eol=lf
 8 | *.sh            text eol=lf
 9 | *.bat           text eol=crlf
10 | *.cmd           text eol=crlf
11 | *.jar           binary
12 | 
13 | src/test/resources/samples/*.txt text eol=lf
14 | src/test/resources/samples/*.out text eol=lf
15 | 


--------------------------------------------------------------------------------
/.github/pull_request_template.md:
--------------------------------------------------------------------------------
 1 | #### Check List:
 2 | - [ ] Tests pass (`./test.sh <username>` shows no differences between expected and actual outputs)
 3 | - [ ] All formatting changes by the build are committed
 4 | - [ ] Your launch script is named `calculate_average_<username>.sh` (make sure to match casing of your GH user name) and is executable
 5 | - [ ] Output matches that of `calculate_average_baseline.sh`
 6 | * Execution time:
 7 | * Execution time of reference implementation:
 8 | 
 9 | <!--
10 | Thanks for your submission. Please go through the checklist above before submitting your pull request.
11 | Use [x] to mark that the item has been completed.
12 | 
13 | Please submit only submissions that are taking less than 1 minute.
14 | 
15 | Please make sure that you have followed the defined rules (https://github.com/gunnarmorling/1brc?tab=readme-ov-file#rules-and-limits).
16 | -->
17 | 


--------------------------------------------------------------------------------
/.github/workflows/maven.yml:
--------------------------------------------------------------------------------
 1 | #
 2 | #  Copyright 2023 The original authors
 3 | #
 4 | #  Licensed under the Apache License, Version 2.0 (the "License");
 5 | #  you may not use this file except in compliance with the License.
 6 | #  You may obtain a copy of the License at
 7 | #
 8 | #      http://www.apache.org/licenses/LICENSE-2.0
 9 | #
10 | #  Unless required by applicable law or agreed to in writing, software
11 | #  distributed under the License is distributed on an "AS IS" BASIS,
12 | #  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
13 | #  See the License for the specific language governing permissions and
14 | #  limitations under the License.
15 | #
16 | 
17 | name: Build
18 | 
19 | on:
20 |   push:
21 |     branches: [ main ]
22 |   pull_request:
23 |     branches: [ main ]
24 | 
25 | jobs:
26 |   build:
27 |     runs-on: ubuntu-latest
28 | 
29 |     steps:
30 |       - name: 'Check out repository'
31 |         uses: actions/checkout@v2
32 |         with:
33 |           submodules: 'true'
34 | 
35 |       - name: 'Set up Java'
36 |         uses: actions/setup-java@v2
37 |         with:
38 |           java-version: 21
39 |           distribution: 'temurin'
40 | 
41 |       - name: 'Cache Maven packages'
42 |         uses: actions/cache@v3
43 |         with:
44 |           path: ~/.m2
45 |           key: ${{ runner.os }}-m2-${{ hashFiles('**/pom.xml') }}
46 |           restore-keys: ${{ runner.os }}-m2
47 | 
48 |       - name: 'Build project'
49 |         run: mvn -B clean verify -Pci
50 | 


--------------------------------------------------------------------------------
/.gitignore:
--------------------------------------------------------------------------------
 1 | #Maven
 2 | target/
 3 | pom.xml.tag
 4 | pom.xml.releaseBackup
 5 | pom.xml.versionsBackup
 6 | release.properties
 7 | 
 8 | # Eclipse
 9 | .project
10 | .classpath
11 | .settings/
12 | bin/
13 | 
14 | # IntelliJ
15 | .idea
16 | *.ipr
17 | *.iml
18 | *.iws
19 | 
20 | # NetBeans
21 | nb-configuration.xml
22 | 
23 | # Visual Studio Code
24 | .vscode
25 | .factorypath
26 | 
27 | # OSX
28 | .DS_Store
29 | 
30 | # Vim
31 | *.swp
32 | *.swo
33 | 
34 | # patch
35 | *.orig
36 | *.rej
37 | 
38 | # Local environment
39 | .env
40 | 
41 | #JReleaser
42 | out/
43 | 
44 | # 1BRC
45 | /measurements*.txt
46 | /*.out
47 | out_expected.txt
48 | node_modules
49 | 


--------------------------------------------------------------------------------
/.mvn/wrapper/maven-wrapper.jar:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/1brc/nodejs/9975dfbfa32143fb7502e63374a48f9fde1c381d/.mvn/wrapper/maven-wrapper.jar


--------------------------------------------------------------------------------
/.mvn/wrapper/maven-wrapper.properties:
--------------------------------------------------------------------------------
 1 | # Licensed to the Apache Software Foundation (ASF) under one
 2 | # or more contributor license agreements.  See the NOTICE file
 3 | # distributed with this work for additional information
 4 | # regarding copyright ownership.  The ASF licenses this file
 5 | # to you under the Apache License, Version 2.0 (the
 6 | # "License"); you may not use this file except in compliance
 7 | # with the License.  You may obtain a copy of the License at
 8 | #
 9 | #   http://www.apache.org/licenses/LICENSE-2.0
10 | #
11 | # Unless required by applicable law or agreed to in writing,
12 | # software distributed under the License is distributed on an
13 | # "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
14 | # KIND, either express or implied.  See the License for the
15 | # specific language governing permissions and limitations
16 | # under the License.
17 | distributionUrl=https://repo.maven.apache.org/maven2/org/apache/maven/apache-maven/3.8.4/apache-maven-3.8.4-bin.zip
18 | wrapperUrl=https://repo.maven.apache.org/maven2/org/apache/maven/wrapper/maven-wrapper/3.2.0/maven-wrapper-3.2.0.jar
19 | 


--------------------------------------------------------------------------------
/1brc.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/1brc/nodejs/9975dfbfa32143fb7502e63374a48f9fde1c381d/1brc.png


--------------------------------------------------------------------------------
/LICENSE.txt:
--------------------------------------------------------------------------------
  1 | 
  2 |                                  Apache License
  3 |                            Version 2.0, January 2004
  4 |                         http://www.apache.org/licenses/
  5 | 
  6 |    TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
  7 | 
  8 |    1. Definitions.
  9 | 
 10 |       "License" shall mean the terms and conditions for use, reproduction,
 11 |       and distribution as defined by Sections 1 through 9 of this document.
 12 | 
 13 |       "Licensor" shall mean the copyright owner or entity authorized by
 14 |       the copyright owner that is granting the License.
 15 | 
 16 |       "Legal Entity" shall mean the union of the acting entity and all
 17 |       other entities that control, are controlled by, or are under common
 18 |       control with that entity. For the purposes of this definition,
 19 |       "control" means (i) the power, direct or indirect, to cause the
 20 |       direction or management of such entity, whether by contract or
 21 |       otherwise, or (ii) ownership of fifty percent (50%) or more of the
 22 |       outstanding shares, or (iii) beneficial ownership of such entity.
 23 | 
 24 |       "You" (or "Your") shall mean an individual or Legal Entity
 25 |       exercising permissions granted by this License.
 26 | 
 27 |       "Source" form shall mean the preferred form for making modifications,
 28 |       including but not limited to software source code, documentation
 29 |       source, and configuration files.
 30 | 
 31 |       "Object" form shall mean any form resulting from mechanical
 32 |       transformation or translation of a Source form, including but
 33 |       not limited to compiled object code, generated documentation,
 34 |       and conversions to other media types.
 35 | 
 36 |       "Work" shall mean the work of authorship, whether in Source or
 37 |       Object form, made available under the License, as indicated by a
 38 |       copyright notice that is included in or attached to the work
 39 |       (an example is provided in the Appendix below).
 40 | 
 41 |       "Derivative Works" shall mean any work, whether in Source or Object
 42 |       form, that is based on (or derived from) the Work and for which the
 43 |       editorial revisions, annotations, elaborations, or other modifications
 44 |       represent, as a whole, an original work of authorship. For the purposes
 45 |       of this License, Derivative Works shall not include works that remain
 46 |       separable from, or merely link (or bind by name) to the interfaces of,
 47 |       the Work and Derivative Works thereof.
 48 | 
 49 |       "Contribution" shall mean any work of authorship, including
 50 |       the original version of the Work and any modifications or additions
 51 |       to that Work or Derivative Works thereof, that is intentionally
 52 |       submitted to Licensor for inclusion in the Work by the copyright owner
 53 |       or by an individual or Legal Entity authorized to submit on behalf of
 54 |       the copyright owner. For the purposes of this definition, "submitted"
 55 |       means any form of electronic, verbal, or written communication sent
 56 |       to the Licensor or its representatives, including but not limited to
 57 |       communication on electronic mailing lists, source code control systems,
 58 |       and issue tracking systems that are managed by, or on behalf of, the
 59 |       Licensor for the purpose of discussing and improving the Work, but
 60 |       excluding communication that is conspicuously marked or otherwise
 61 |       designated in writing by the copyright owner as "Not a Contribution."
 62 | 
 63 |       "Contributor" shall mean Licensor and any individual or Legal Entity
 64 |       on behalf of whom a Contribution has been received by Licensor and
 65 |       subsequently incorporated within the Work.
 66 | 
 67 |    2. Grant of Copyright License. Subject to the terms and conditions of
 68 |       this License, each Contributor hereby grants to You a perpetual,
 69 |       worldwide, non-exclusive, no-charge, royalty-free, irrevocable
 70 |       copyright license to reproduce, prepare Derivative Works of,
 71 |       publicly display, publicly perform, sublicense, and distribute the
 72 |       Work and such Derivative Works in Source or Object form.
 73 | 
 74 |    3. Grant of Patent License. Subject to the terms and conditions of
 75 |       this License, each Contributor hereby grants to You a perpetual,
 76 |       worldwide, non-exclusive, no-charge, royalty-free, irrevocable
 77 |       (except as stated in this section) patent license to make, have made,
 78 |       use, offer to sell, sell, import, and otherwise transfer the Work,
 79 |       where such license applies only to those patent claims licensable
 80 |       by such Contributor that are necessarily infringed by their
 81 |       Contribution(s) alone or by combination of their Contribution(s)
 82 |       with the Work to which such Contribution(s) was submitted. If You
 83 |       institute patent litigation against any entity (including a
 84 |       cross-claim or counterclaim in a lawsuit) alleging that the Work
 85 |       or a Contribution incorporated within the Work constitutes direct
 86 |       or contributory patent infringement, then any patent licenses
 87 |       granted to You under this License for that Work shall terminate
 88 |       as of the date such litigation is filed.
 89 | 
 90 |    4. Redistribution. You may reproduce and distribute copies of the
 91 |       Work or Derivative Works thereof in any medium, with or without
 92 |       modifications, and in Source or Object form, provided that You
 93 |       meet the following conditions:
 94 | 
 95 |       (a) You must give any other recipients of the Work or
 96 |           Derivative Works a copy of this License; and
 97 | 
 98 |       (b) You must cause any modified files to carry prominent notices
 99 |           stating that You changed the files; and
100 | 
101 |       (c) You must retain, in the Source form of any Derivative Works
102 |           that You distribute, all copyright, patent, trademark, and
103 |           attribution notices from the Source form of the Work,
104 |           excluding those notices that do not pertain to any part of
105 |           the Derivative Works; and
106 | 
107 |       (d) If the Work includes a "NOTICE" text file as part of its
108 |           distribution, then any Derivative Works that You distribute must
109 |           include a readable copy of the attribution notices contained
110 |           within such NOTICE file, excluding those notices that do not
111 |           pertain to any part of the Derivative Works, in at least one
112 |           of the following places: within a NOTICE text file distributed
113 |           as part of the Derivative Works; within the Source form or
114 |           documentation, if provided along with the Derivative Works; or,
115 |           within a display generated by the Derivative Works, if and
116 |           wherever such third-party notices normally appear. The contents
117 |           of the NOTICE file are for informational purposes only and
118 |           do not modify the License. You may add Your own attribution
119 |           notices within Derivative Works that You distribute, alongside
120 |           or as an addendum to the NOTICE text from the Work, provided
121 |           that such additional attribution notices cannot be construed
122 |           as modifying the License.
123 | 
124 |       You may add Your own copyright statement to Your modifications and
125 |       may provide additional or different license terms and conditions
126 |       for use, reproduction, or distribution of Your modifications, or
127 |       for any such Derivative Works as a whole, provided Your use,
128 |       reproduction, and distribution of the Work otherwise complies with
129 |       the conditions stated in this License.
130 | 
131 |    5. Submission of Contributions. Unless You explicitly state otherwise,
132 |       any Contribution intentionally submitted for inclusion in the Work
133 |       by You to the Licensor shall be under the terms and conditions of
134 |       this License, without any additional terms or conditions.
135 |       Notwithstanding the above, nothing herein shall supersede or modify
136 |       the terms of any separate license agreement you may have executed
137 |       with Licensor regarding such Contributions.
138 | 
139 |    6. Trademarks. This License does not grant permission to use the trade
140 |       names, trademarks, service marks, or product names of the Licensor,
141 |       except as required for reasonable and customary use in describing the
142 |       origin of the Work and reproducing the content of the NOTICE file.
143 | 
144 |    7. Disclaimer of Warranty. Unless required by applicable law or
145 |       agreed to in writing, Licensor provides the Work (and each
146 |       Contributor provides its Contributions) on an "AS IS" BASIS,
147 |       WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
148 |       implied, including, without limitation, any warranties or conditions
149 |       of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
150 |       PARTICULAR PURPOSE. You are solely responsible for determining the
151 |       appropriateness of using or redistributing the Work and assume any
152 |       risks associated with Your exercise of permissions under this License.
153 | 
154 |    8. Limitation of Liability. In no event and under no legal theory,
155 |       whether in tort (including negligence), contract, or otherwise,
156 |       unless required by applicable law (such as deliberate and grossly
157 |       negligent acts) or agreed to in writing, shall any Contributor be
158 |       liable to You for damages, including any direct, indirect, special,
159 |       incidental, or consequential damages of any character arising as a
160 |       result of this License or out of the use or inability to use the
161 |       Work (including but not limited to damages for loss of goodwill,
162 |       work stoppage, computer failure or malfunction, or any and all
163 |       other commercial damages or losses), even if such Contributor
164 |       has been advised of the possibility of such damages.
165 | 
166 |    9. Accepting Warranty or Additional Liability. While redistributing
167 |       the Work or Derivative Works thereof, You may choose to offer,
168 |       and charge a fee for, acceptance of support, warranty, indemnity,
169 |       or other liability obligations and/or rights consistent with this
170 |       License. However, in accepting such obligations, You may act only
171 |       on Your own behalf and on Your sole responsibility, not on behalf
172 |       of any other Contributor, and only if You agree to indemnify,
173 |       defend, and hold each Contributor harmless for any liability
174 |       incurred by, or claims asserted against, such Contributor by reason
175 |       of your accepting any such warranty or additional liability.
176 | 
177 |    END OF TERMS AND CONDITIONS
178 | 
179 |    APPENDIX: How to apply the Apache License to your work.
180 | 
181 |       To apply the Apache License to your work, attach the following
182 |       boilerplate notice, with the fields enclosed by brackets "[]"
183 |       replaced with your own identifying information. (Don't include
184 |       the brackets!)  The text should be enclosed in the appropriate
185 |       comment syntax for the file format. We also recommend that a
186 |       file or class name and description of purpose be included on the
187 |       same "printed page" as the copyright notice for easier
188 |       identification within third-party archives.
189 | 
190 |    Copyright [yyyy] [name of copyright owner]
191 | 
192 |    Licensed under the Apache License, Version 2.0 (the "License");
193 |    you may not use this file except in compliance with the License.
194 |    You may obtain a copy of the License at
195 | 
196 |        http://www.apache.org/licenses/LICENSE-2.0
197 | 
198 |    Unless required by applicable law or agreed to in writing, software
199 |    distributed under the License is distributed on an "AS IS" BASIS,
200 |    WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
201 |    See the License for the specific language governing permissions and
202 |    limitations under the License.


--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
  1 | # 1️⃣🐝🏎️ The One Billion Row Challenge with Node.js
  2 | 
  3 | ## About the Challenge
  4 | 
  5 | The One Billion Row Challenge (1BRC) is a fun exploration of how far modern Java can be pushed for aggregating one billion rows from a text file.
  6 | 
  7 | Later the community created a dedicated @1brc organization to pay more attention to the implementations in other languages. This repository contains and accepts Node.js based implementations.
  8 | 
  9 | Grab all your (virtual) threads, reach out to SIMD, optimize your GC, or pull any other trick, and create the fastest implementation for solving this task!
 10 | 
 11 | <img src="1brc.png" alt="1BRC" style="display: block; margin-left: auto; margin-right: auto; margin-bottom:1em; width: 50%;">
 12 | 
 13 | The text file contains temperature values for a range of weather stations.
 14 | Each row is one measurement in the format `<string: station name>;<double: measurement>`, with the measurement value having exactly one fractional digit.
 15 | The following shows ten rows as an example:
 16 | 
 17 | ```
 18 | Hamburg;12.0
 19 | Bulawayo;8.9
 20 | Palembang;38.8
 21 | St. John's;15.2
 22 | Cracow;12.6
 23 | Bridgetown;26.9
 24 | Istanbul;6.2
 25 | Roseau;34.4
 26 | Conakry;31.2
 27 | Istanbul;23.0
 28 | ```
 29 | 
 30 | The task is to write a program which reads the file, calculates the min, mean, and max temperature value per weather station, and emits the results on stdout like this
 31 | (i.e. sorted alphabetically by station name, and the result values per station in the format `<min>/<mean>/<max>`, rounded to one fractional digit):
 32 | 
 33 | ```
 34 | {Abha=-23.0/18.0/59.2, Abidjan=-16.2/26.0/67.3, Abéché=-10.0/29.4/69.0, Accra=-10.1/26.4/66.4, Addis Ababa=-23.7/16.0/67.0, Adelaide=-27.8/17.3/58.5, ...}
 35 | ```
 36 | 
 37 | Submit your implementation and become part of the leaderboard!
 38 | 
 39 | ## Results
 40 | 
 41 | | #   | Result (m:s.ms) | Implementation                                                                        | Submitter                                        | Notes                                                                              |
 42 | | --- | --------------- | ------------------------------------------------------------------------------------- | ------------------------------------------------ | ---------------------------------------------------------------------------------- |
 43 | | 1.  | 00:23.000       | [link](https://github.com/1brc/nodejs/blob/main/src/main/nodejs/Edgar-P-yan/index.js) | [Edgar Pogosyan](https://github.com/Edgar-P-yan) | Multi-threaded, optimized parsing, input-specific `float` to `int` parser, no mmap |
 44 | |     | 06:16.000       | [link](https://github.com/1brc/nodejs/blob/main/src/main/nodejs/baseline/index.js)    | [Edgar Pogosyan](https://github.com/Edgar-P-yan) | The baseline, single threaded, naive implementation                                |
 45 | 
 46 | See [below](#entering-the-challenge) for instructions how to enter the challenge with your own implementation.
 47 | 
 48 | ## Prerequisites
 49 | 
 50 | 1. [Java 21](https://openjdk.org/projects/jdk/21/) to generate the `measurements.txt` files and optionally run tests.
 51 | 2. Node.js, preferably via nvm (node version manager) must be installed on your system.
 52 | 
 53 | ## Running the Challenge
 54 | 
 55 | This repository contains two programs:
 56 | 
 57 | - `dev.morling.onebrc.CreateMeasurements` (invoked via _create_measurements.sh_): Creates the file _measurements.txt_ in the root directory of this project with a configurable number of random measurement values
 58 | - `src/main/nodejs/baseline/index.js` (invoked via _calculate_average_baseline.sh_): Calculates the average values for the file _measurements.txt_
 59 | 
 60 | Execute the following steps to run the challenge:
 61 | 
 62 | 1. Build the project using Apache Maven:
 63 | 
 64 |    ```
 65 |    ./mvnw clean verify
 66 |    ```
 67 | 
 68 | 2. Create the measurements file with 1B rows (just once):
 69 | 
 70 |    ```
 71 |    ./create_measurements.sh 1000000000
 72 |    ```
 73 | 
 74 |    This will take a few minutes.
 75 |    **Attention:** the generated file has a size of approx. **12 GB**, so make sure to have enough diskspace.
 76 | 
 77 | 3. Calculate the average measurement values:
 78 | 
 79 |    ```
 80 |    ./calculate_average_baseline.sh
 81 |    ```
 82 | 
 83 |    The provided naive example implementation uses the Node.js Streams for processing the file and completes the task in ~6m16s on environment used for [result evaluation](#evaluating-results).
 84 |    It serves as the base line for comparing your own implementation.
 85 | 
 86 | 4. Optimize the heck out of it:
 87 | 
 88 |    Adjust the `src/main/nodejs/baseline/index.js` program to speed it up, in any way you see fit (just sticking to a few rules described below).
 89 |    Options include parallelizing the computation, memory-mapping different sections of the file concurrently, choosing and tuning the garbage collector, and much more.
 90 | 
 91 | ## Flamegraph/Profiling
 92 | 
 93 | > TODO: add instructions on how to profile node.js programs
 94 | 
 95 | ## Rules and limits
 96 | 
 97 | - No external library dependencies may be used
 98 | <!-- - Implementations must be provided as a single source file -->
 99 | - The computation must happen at application _runtime_, i.e. you cannot process the measurements file at _build time_
100 |   and just bake the result into the binary
101 | - Input value ranges are as follows:
102 |   - Station name: non null UTF-8 string of min length 1 character and max length 100 bytes (i.e. this could be 100 one-byte characters, or 50 two-byte characters, etc.)
103 |   - Temperature value: non null double between -99.9 (inclusive) and 99.9 (inclusive), always with one fractional digit
104 | - There is a maximum of 10,000 unique station names
105 | - Implementations must not rely on specifics of a given data set, e.g. any valid station name as per the constraints above and any data distribution (number of measurements per station) must be supported
106 | 
107 | ## Entering the Challenge
108 | 
109 | To submit your own implementation to 1BRC, follow these steps:
110 | 
111 | - Create a fork of the [1brc/nodejs](https://github.com/1brc/nodejs/) GitHub repository.
112 | - Create a copy of `src/main/nodejs/baseline` directory, rename it to `src/main/nodejs/<your_GH_user>`, e.g. `src/main/nodejs/JohnDoe`.
113 | - Make that implementation fast. Really fast.
114 | - Create a copy of _calculate_average_baseline.sh_, named _calculate_average\_<your_GH_user>.sh_, e.g. _calculate_average_JohnDoe.sh_.
115 | - Adjust that script so that it references your implementation file. If needed, provide any Node.js/V8 runtime arguments.
116 |   Make sure that script does not write anything to standard output other than calculation results.
117 | - Run the test suite by executing _/test.sh <your_GH_user>_; if any differences are reported, fix them before submitting your implementation.
118 | - Create a pull request against the upstream repository, clearly stating
119 |   - The execution time of the program on your system and specs of the same (CPU, number of cores, RAM). This is for informative purposes only, the official runtime will be determined as described below.
120 | - I will run the program and determine its performance as described in the next section, and enter the result to the scoreboard.
121 | 
122 | **Note:** I reserve the right to not evaluate specific submissions if I feel doubtful about the implementation (I.e. I won't run your Bitcoin miner ;).
123 | 
124 | <!-- If you'd like to discuss any potential ideas for implementing 1BRC with the community,
125 | you can use the [GitHub Discussions](https://github.com/gunnarmorling/onebrc/discussions) of this repository.
126 | Please keep it friendly and civil. -->
127 | 
128 | ## Evaluating Results
129 | 
130 | For now results are determined by running the program on a Apple MacBook M1 32GB (10 physical).
131 | The `time` program is used for measuring execution times, i.e. end-to-end times are measured.
132 | Each contender will be run five times in a row.
133 | The slowest and the fastest runs are discarded.
134 | The mean value of the remaining three runs is the result for that contender and will be added to the results table above.
135 | The exact same _measurements.txt_ file is used for evaluating all contenders.
136 | 
137 | <!-- If you'd like to spin up your own box for testing on Hetzner Cloud, you may find these [set-up scripts](https://github.com/gunnarmorling/cloud-boxes/) (based on Terraform and Ansible) useful.
138 | It has been reported that instances of the CCX33 machine class can significantly vary in terms of performance,
139 | so results are only comparable when obtained from one and the same instance.
140 | Note this will incur cost you are responsible for, I am not going to pay your cloud bill :) -->
141 | 
142 | <!-- ## Prize
143 | 
144 | If you enter this challenge, you may learn something new, get to inspire others, and take pride in seeing your name listed in the scoreboard above.
145 | Rumor has it that the winner may receive a unique 1️⃣🐝🏎️ t-shirt, too! -->
146 | 
147 | ## FAQ
148 | 
149 | <!-- _Q: Can I use Kotlin or other JVM languages other than Java?_\
150 | A: No, this challenge is focussed on Java only. Feel free to inofficially share implementations significantly outperforming any listed results, though.
151 | 
152 | _Q: Can I use non-JVM languages and/or tools?_\
153 | A: No, this challenge is focussed on Java only. Feel free to inofficially share interesting implementations and results though. For instance it would be interesting to see how DuckDB fares with this task.
154 | 
155 | _Q: I've got an implementation—but it's not in Java. Can I share it somewhere?_\
156 | A: Whilst non-Java solutions cannot be formally submitted to the challenge, you are welcome to share them over in the [Show and tell](https://github.com/gunnarmorling/1brc/discussions/categories/show-and-tell) GitHub discussion area.
157 | 
158 | _Q: Can I use JNI?_\
159 | A: Submissions must be completely implemented in Java, i.e. you cannot write JNI glue code in C/C++. You could use AOT compilation of Java code via GraalVM though, either by AOT-compiling the entire application, or by creating a native library (see [here](https://www.graalvm.org/22.0/reference-manual/native-image/ImplementingNativeMethodsInJavaWithSVM/). -->
160 | 
161 | _Q: What is the encoding of the measurements.txt file?_\
162 | A: The file is encoded with UTF-8.
163 | 
164 | _Q: Can I make assumptions on the names of the weather stations showing up in the data set?_\
165 | A: No, while only a fixed set of station names is used by the data set generator, any solution should work with arbitrary UTF-8 station names
166 | (for the sake of simplicity, names are guaranteed to contain no `;` character).
167 | 
168 | _Q: Can I copy code from other submissions?_\
169 | A: Yes, you can. The primary focus of the challenge is about learning something new, rather than "winning". When you do so, please give credit to the relevant source submissions. Please don't re-submit other entries with no or only trivial improvements.
170 | 
171 | _Q: Which operating system is used for evaluation?_\
172 | A: macOS Sonoma 14 (see [Evaluating Results](#evaluating-results))
173 | 
174 | _Q: My solution runs in 2 sec on my machine. Am I the fastest 1BRC-er in the world?_\
175 | A: Probably not :) 1BRC results are reported in wallclock time, thus results of different implementations are only comparable when obtained on the same machine. If for instance an implementation is faster on a 32 core workstation than on the 8 core evaluation instance, this doesn't allow for any conclusions. When sharing 1BRC results, you should also always share the result of running the baseline implementation on the same hardware.
176 | 
177 | _Q: Why_ 1️⃣🐝🏎️ _?_\
178 | A: It's the abbreviation of the project name: **One** **B**illion **R**ow **C**hallenge.
179 | 
180 | ## License
181 | 
182 | This code base is available under the Apache License, version 2.
183 | 
184 | ## Code of Conduct
185 | 
186 | Be excellent to each other!
187 | More than winning, the purpose of this challenge is to have fun and learn something new.
188 | 


--------------------------------------------------------------------------------
/additional_build_step_thomaswue.sh:
--------------------------------------------------------------------------------
 1 | #!/bin/sh
 2 | #
 3 | #  Copyright 2023 The original authors
 4 | #
 5 | #  Licensed under the Apache License, Version 2.0 (the "License");
 6 | #  you may not use this file except in compliance with the License.
 7 | #  You may obtain a copy of the License at
 8 | #
 9 | #      http://www.apache.org/licenses/LICENSE-2.0
10 | #
11 | #  Unless required by applicable law or agreed to in writing, software
12 | #  distributed under the License is distributed on an "AS IS" BASIS,
13 | #  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
14 | #  See the License for the specific language governing permissions and
15 | #  limitations under the License.
16 | #
17 | 
18 | source "$HOME/.sdkman/bin/sdkman-init.sh"
19 | sdk use java 21.0.1-graal 1>&2
20 | NATIVE_IMAGE_OPTS="--gc=epsilon -O3 -march=native --enable-preview"
21 | native-image $NATIVE_IMAGE_OPTS -cp target/average-1.0.0-SNAPSHOT.jar -o image_calculateaverage_thomaswue dev.morling.onebrc.CalculateAverage_thomaswue
22 | 


--------------------------------------------------------------------------------
/calculate_average_Edgar-P-Yan.sh:
--------------------------------------------------------------------------------
 1 | #!/bin/sh
 2 | #
 3 | #  Copyright 2023 The original authors
 4 | #
 5 | #  Licensed under the Apache License, Version 2.0 (the "License");
 6 | #  you may not use this file except in compliance with the License.
 7 | #  You may obtain a copy of the License at
 8 | #
 9 | #      http://www.apache.org/licenses/LICENSE-2.0
10 | #
11 | #  Unless required by applicable law or agreed to in writing, software
12 | #  distributed under the License is distributed on an "AS IS" BASIS,
13 | #  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
14 | #  See the License for the specific language governing permissions and
15 | #  limitations under the License.
16 | #
17 | 
18 | time node src/main/nodejs/Edgar-P-yan/index.js measurements.txt
19 | 


--------------------------------------------------------------------------------
/calculate_average_baseline.sh:
--------------------------------------------------------------------------------
 1 | #!/bin/sh
 2 | #
 3 | #  Copyright 2023 The original authors
 4 | #
 5 | #  Licensed under the Apache License, Version 2.0 (the "License");
 6 | #  you may not use this file except in compliance with the License.
 7 | #  You may obtain a copy of the License at
 8 | #
 9 | #      http://www.apache.org/licenses/LICENSE-2.0
10 | #
11 | #  Unless required by applicable law or agreed to in writing, software
12 | #  distributed under the License is distributed on an "AS IS" BASIS,
13 | #  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
14 | #  See the License for the specific language governing permissions and
15 | #  limitations under the License.
16 | #
17 | 
18 | time node src/main/nodejs/baseline/index.js measurements.txt
19 | 


--------------------------------------------------------------------------------
/cleanup.sh:
--------------------------------------------------------------------------------
 1 | #!/bin/sh
 2 | #
 3 | #  Copyright 2023 The original authors
 4 | #
 5 | #  Licensed under the Apache License, Version 2.0 (the "License");
 6 | #  you may not use this file except in compliance with the License.
 7 | #  You may obtain a copy of the License at
 8 | #
 9 | #      http://www.apache.org/licenses/LICENSE-2.0
10 | #
11 | #  Unless required by applicable law or agreed to in writing, software
12 | #  distributed under the License is distributed on an "AS IS" BASIS,
13 | #  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
14 | #  See the License for the specific language governing permissions and
15 | #  limitations under the License.
16 | #
17 | 
18 | if [ -z "$1" ]
19 |   then
20 |     echo "Usage: cleanup.sh <fork name>"
21 |     exit 1
22 | fi
23 | 
24 | git checkout .
25 | git checkout main
26 | git branch -D $1
27 | git pull upstream main
28 | 


--------------------------------------------------------------------------------
/create_measurements.sh:
--------------------------------------------------------------------------------
 1 | #!/bin/sh
 2 | #
 3 | #  Copyright 2023 The original authors
 4 | #
 5 | #  Licensed under the Apache License, Version 2.0 (the "License");
 6 | #  you may not use this file except in compliance with the License.
 7 | #  You may obtain a copy of the License at
 8 | #
 9 | #      http://www.apache.org/licenses/LICENSE-2.0
10 | #
11 | #  Unless required by applicable law or agreed to in writing, software
12 | #  distributed under the License is distributed on an "AS IS" BASIS,
13 | #  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
14 | #  See the License for the specific language governing permissions and
15 | #  limitations under the License.
16 | #
17 | 
18 | 
19 | java --class-path target/average-1.0.0-SNAPSHOT.jar dev.morling.onebrc.CreateMeasurements $1
20 | 


--------------------------------------------------------------------------------
/create_measurements2.sh:
--------------------------------------------------------------------------------
 1 | #!/bin/sh
 2 | #
 3 | #  Copyright 2023 The original authors
 4 | #
 5 | #  Licensed under the Apache License, Version 2.0 (the "License");
 6 | #  you may not use this file except in compliance with the License.
 7 | #  You may obtain a copy of the License at
 8 | #
 9 | #      http://www.apache.org/licenses/LICENSE-2.0
10 | #
11 | #  Unless required by applicable law or agreed to in writing, software
12 | #  distributed under the License is distributed on an "AS IS" BASIS,
13 | #  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
14 | #  See the License for the specific language governing permissions and
15 | #  limitations under the License.
16 | #
17 | 
18 | 
19 | java --class-path target/average-1.0.0-SNAPSHOT.jar dev.morling.onebrc.CreateMeasurements2 $1
20 | 


--------------------------------------------------------------------------------
/create_measurements3.sh:
--------------------------------------------------------------------------------
 1 | #!/bin/sh
 2 | #
 3 | #  Copyright 2023 The original authors
 4 | #
 5 | #  Licensed under the Apache License, Version 2.0 (the "License");
 6 | #  you may not use this file except in compliance with the License.
 7 | #  You may obtain a copy of the License at
 8 | #
 9 | #      http://www.apache.org/licenses/LICENSE-2.0
10 | #
11 | #  Unless required by applicable law or agreed to in writing, software
12 | #  distributed under the License is distributed on an "AS IS" BASIS,
13 | #  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
14 | #  See the License for the specific language governing permissions and
15 | #  limitations under the License.
16 | #
17 | 
18 | 
19 | java --class-path target/average-1.0.0-SNAPSHOT.jar dev.morling.onebrc.CreateMeasurements3 $1
20 | 


--------------------------------------------------------------------------------
/etc/license.txt:
--------------------------------------------------------------------------------
 1 |  Copyright 2023 The original authors
 2 | 
 3 |  Licensed under the Apache License, Version 2.0 (the "License");
 4 |  you may not use this file except in compliance with the License.
 5 |  You may obtain a copy of the License at
 6 | 
 7 |      http://www.apache.org/licenses/LICENSE-2.0
 8 | 
 9 |  Unless required by applicable law or agreed to in writing, software
10 |  distributed under the License is distributed on an "AS IS" BASIS,
11 |  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
12 |  See the License for the specific language governing permissions and
13 |  limitations under the License.
14 | 


--------------------------------------------------------------------------------
/eval.sh:
--------------------------------------------------------------------------------
 1 | #!/bin/sh
 2 | #
 3 | #  Copyright 2023 The original authors
 4 | #
 5 | #  Licensed under the Apache License, Version 2.0 (the "License");
 6 | #  you may not use this file except in compliance with the License.
 7 | #  You may obtain a copy of the License at
 8 | #
 9 | #      http://www.apache.org/licenses/LICENSE-2.0
10 | #
11 | #  Unless required by applicable law or agreed to in writing, software
12 | #  distributed under the License is distributed on an "AS IS" BASIS,
13 | #  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
14 | #  See the License for the specific language governing permissions and
15 | #  limitations under the License.
16 | #
17 | 
18 | if [ -z "$1" ]
19 |   then
20 |     echo "Usage: eval.sh <fork name>"
21 |     exit 1
22 | fi
23 | 
24 | ./evaluate.sh $1 2>&1 | tee $1.out
25 | 


--------------------------------------------------------------------------------
/evaluate.sh:
--------------------------------------------------------------------------------
 1 | #!/bin/sh
 2 | #
 3 | #  Copyright 2023 The original authors
 4 | #
 5 | #  Licensed under the Apache License, Version 2.0 (the "License");
 6 | #  you may not use this file except in compliance with the License.
 7 | #  You may obtain a copy of the License at
 8 | #
 9 | #      http://www.apache.org/licenses/LICENSE-2.0
10 | #
11 | #  Unless required by applicable law or agreed to in writing, software
12 | #  distributed under the License is distributed on an "AS IS" BASIS,
13 | #  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
14 | #  See the License for the specific language governing permissions and
15 | #  limitations under the License.
16 | #
17 | 
18 | if [ -z "$1" ]
19 |   then
20 |     echo "Usage: evaluate.sh <fork name>"
21 |     exit 1
22 | fi
23 | 
24 | java --version
25 | 
26 | mvn clean verify
27 | 
28 | rm -f measurements.txt
29 | ln -s measurements_1B.txt measurements.txt
30 | 
31 | for i in {1..5}
32 | do
33 |     ./calculate_average_$1.sh
34 | done
35 | 


--------------------------------------------------------------------------------
/mvnw:
--------------------------------------------------------------------------------
  1 | #!/bin/sh
  2 | # ----------------------------------------------------------------------------
  3 | # Licensed to the Apache Software Foundation (ASF) under one
  4 | # or more contributor license agreements.  See the NOTICE file
  5 | # distributed with this work for additional information
  6 | # regarding copyright ownership.  The ASF licenses this file
  7 | # to you under the Apache License, Version 2.0 (the
  8 | # "License"); you may not use this file except in compliance
  9 | # with the License.  You may obtain a copy of the License at
 10 | #
 11 | #    http://www.apache.org/licenses/LICENSE-2.0
 12 | #
 13 | # Unless required by applicable law or agreed to in writing,
 14 | # software distributed under the License is distributed on an
 15 | # "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
 16 | # KIND, either express or implied.  See the License for the
 17 | # specific language governing permissions and limitations
 18 | # under the License.
 19 | # ----------------------------------------------------------------------------
 20 | 
 21 | # ----------------------------------------------------------------------------
 22 | # Apache Maven Wrapper startup batch script, version 3.2.0
 23 | #
 24 | # Required ENV vars:
 25 | # ------------------
 26 | #   JAVA_HOME - location of a JDK home dir
 27 | #
 28 | # Optional ENV vars
 29 | # -----------------
 30 | #   MAVEN_OPTS - parameters passed to the Java VM when running Maven
 31 | #     e.g. to debug Maven itself, use
 32 | #       set MAVEN_OPTS=-Xdebug -Xrunjdwp:transport=dt_socket,server=y,suspend=y,address=8000
 33 | #   MAVEN_SKIP_RC - flag to disable loading of mavenrc files
 34 | # ----------------------------------------------------------------------------
 35 | 
 36 | if [ -z "$MAVEN_SKIP_RC" ] ; then
 37 | 
 38 |   if [ -f /usr/local/etc/mavenrc ] ; then
 39 |     . /usr/local/etc/mavenrc
 40 |   fi
 41 | 
 42 |   if [ -f /etc/mavenrc ] ; then
 43 |     . /etc/mavenrc
 44 |   fi
 45 | 
 46 |   if [ -f "$HOME/.mavenrc" ] ; then
 47 |     . "$HOME/.mavenrc"
 48 |   fi
 49 | 
 50 | fi
 51 | 
 52 | # OS specific support.  $var _must_ be set to either true or false.
 53 | cygwin=false;
 54 | darwin=false;
 55 | mingw=false
 56 | case "$(uname)" in
 57 |   CYGWIN*) cygwin=true ;;
 58 |   MINGW*) mingw=true;;
 59 |   Darwin*) darwin=true
 60 |     # Use /usr/libexec/java_home if available, otherwise fall back to /Library/Java/Home
 61 |     # See https://developer.apple.com/library/mac/qa/qa1170/_index.html
 62 |     if [ -z "$JAVA_HOME" ]; then
 63 |       if [ -x "/usr/libexec/java_home" ]; then
 64 |         JAVA_HOME="$(/usr/libexec/java_home)"; export JAVA_HOME
 65 |       else
 66 |         JAVA_HOME="/Library/Java/Home"; export JAVA_HOME
 67 |       fi
 68 |     fi
 69 |     ;;
 70 | esac
 71 | 
 72 | if [ -z "$JAVA_HOME" ] ; then
 73 |   if [ -r /etc/gentoo-release ] ; then
 74 |     JAVA_HOME=$(java-config --jre-home)
 75 |   fi
 76 | fi
 77 | 
 78 | # For Cygwin, ensure paths are in UNIX format before anything is touched
 79 | if $cygwin ; then
 80 |   [ -n "$JAVA_HOME" ] &&
 81 |     JAVA_HOME=$(cygpath --unix "$JAVA_HOME")
 82 |   [ -n "$CLASSPATH" ] &&
 83 |     CLASSPATH=$(cygpath --path --unix "$CLASSPATH")
 84 | fi
 85 | 
 86 | # For Mingw, ensure paths are in UNIX format before anything is touched
 87 | if $mingw ; then
 88 |   [ -n "$JAVA_HOME" ] && [ -d "$JAVA_HOME" ] &&
 89 |     JAVA_HOME="$(cd "$JAVA_HOME" || (echo "cannot cd into $JAVA_HOME."; exit 1); pwd)"
 90 | fi
 91 | 
 92 | if [ -z "$JAVA_HOME" ]; then
 93 |   javaExecutable="$(which javac)"
 94 |   if [ -n "$javaExecutable" ] && ! [ "$(expr "\"$javaExecutable\"" : '\([^ ]*\)')" = "no" ]; then
 95 |     # readlink(1) is not available as standard on Solaris 10.
 96 |     readLink=$(which readlink)
 97 |     if [ ! "$(expr "$readLink" : '\([^ ]*\)')" = "no" ]; then
 98 |       if $darwin ; then
 99 |         javaHome="$(dirname "\"$javaExecutable\"")"
100 |         javaExecutable="$(cd "\"$javaHome\"" && pwd -P)/javac"
101 |       else
102 |         javaExecutable="$(readlink -f "\"$javaExecutable\"")"
103 |       fi
104 |       javaHome="$(dirname "\"$javaExecutable\"")"
105 |       javaHome=$(expr "$javaHome" : '\(.*\)/bin')
106 |       JAVA_HOME="$javaHome"
107 |       export JAVA_HOME
108 |     fi
109 |   fi
110 | fi
111 | 
112 | if [ -z "$JAVACMD" ] ; then
113 |   if [ -n "$JAVA_HOME"  ] ; then
114 |     if [ -x "$JAVA_HOME/jre/sh/java" ] ; then
115 |       # IBM's JDK on AIX uses strange locations for the executables
116 |       JAVACMD="$JAVA_HOME/jre/sh/java"
117 |     else
118 |       JAVACMD="$JAVA_HOME/bin/java"
119 |     fi
120 |   else
121 |     JAVACMD="$(\unset -f command 2>/dev/null; \command -v java)"
122 |   fi
123 | fi
124 | 
125 | if [ ! -x "$JAVACMD" ] ; then
126 |   echo "Error: JAVA_HOME is not defined correctly." >&2
127 |   echo "  We cannot execute $JAVACMD" >&2
128 |   exit 1
129 | fi
130 | 
131 | if [ -z "$JAVA_HOME" ] ; then
132 |   echo "Warning: JAVA_HOME environment variable is not set."
133 | fi
134 | 
135 | # traverses directory structure from process work directory to filesystem root
136 | # first directory with .mvn subdirectory is considered project base directory
137 | find_maven_basedir() {
138 |   if [ -z "$1" ]
139 |   then
140 |     echo "Path not specified to find_maven_basedir"
141 |     return 1
142 |   fi
143 | 
144 |   basedir="$1"
145 |   wdir="$1"
146 |   while [ "$wdir" != '/' ] ; do
147 |     if [ -d "$wdir"/.mvn ] ; then
148 |       basedir=$wdir
149 |       break
150 |     fi
151 |     # workaround for JBEAP-8937 (on Solaris 10/Sparc)
152 |     if [ -d "${wdir}" ]; then
153 |       wdir=$(cd "$wdir/.." || exit 1; pwd)
154 |     fi
155 |     # end of workaround
156 |   done
157 |   printf '%s' "$(cd "$basedir" || exit 1; pwd)"
158 | }
159 | 
160 | # concatenates all lines of a file
161 | concat_lines() {
162 |   if [ -f "$1" ]; then
163 |     # Remove \r in case we run on Windows within Git Bash
164 |     # and check out the repository with auto CRLF management
165 |     # enabled. Otherwise, we may read lines that are delimited with
166 |     # \r\n and produce $'-Xarg\r' rather than -Xarg due to word
167 |     # splitting rules.
168 |     tr -s '\r\n' ' ' < "$1"
169 |   fi
170 | }
171 | 
172 | log() {
173 |   if [ "$MVNW_VERBOSE" = true ]; then
174 |     printf '%s\n' "$1"
175 |   fi
176 | }
177 | 
178 | BASE_DIR=$(find_maven_basedir "$(dirname "$0")")
179 | if [ -z "$BASE_DIR" ]; then
180 |   exit 1;
181 | fi
182 | 
183 | MAVEN_PROJECTBASEDIR=${MAVEN_BASEDIR:-"$BASE_DIR"}; export MAVEN_PROJECTBASEDIR
184 | log "$MAVEN_PROJECTBASEDIR"
185 | 
186 | ##########################################################################################
187 | # Extension to allow automatically downloading the maven-wrapper.jar from Maven-central
188 | # This allows using the maven wrapper in projects that prohibit checking in binary data.
189 | ##########################################################################################
190 | wrapperJarPath="$MAVEN_PROJECTBASEDIR/.mvn/wrapper/maven-wrapper.jar"
191 | if [ -r "$wrapperJarPath" ]; then
192 |     log "Found $wrapperJarPath"
193 | else
194 |     log "Couldn't find $wrapperJarPath, downloading it ..."
195 | 
196 |     if [ -n "$MVNW_REPOURL" ]; then
197 |       wrapperUrl="$MVNW_REPOURL/org/apache/maven/wrapper/maven-wrapper/3.2.0/maven-wrapper-3.2.0.jar"
198 |     else
199 |       wrapperUrl="https://repo.maven.apache.org/maven2/org/apache/maven/wrapper/maven-wrapper/3.2.0/maven-wrapper-3.2.0.jar"
200 |     fi
201 |     while IFS="=" read -r key value; do
202 |       # Remove '\r' from value to allow usage on windows as IFS does not consider '\r' as a separator ( considers space, tab, new line ('\n'), and custom '=' )
203 |       safeValue=$(echo "$value" | tr -d '\r')
204 |       case "$key" in (wrapperUrl) wrapperUrl="$safeValue"; break ;;
205 |       esac
206 |     done < "$MAVEN_PROJECTBASEDIR/.mvn/wrapper/maven-wrapper.properties"
207 |     log "Downloading from: $wrapperUrl"
208 | 
209 |     if $cygwin; then
210 |       wrapperJarPath=$(cygpath --path --windows "$wrapperJarPath")
211 |     fi
212 | 
213 |     if command -v wget > /dev/null; then
214 |         log "Found wget ... using wget"
215 |         [ "$MVNW_VERBOSE" = true ] && QUIET="" || QUIET="--quiet"
216 |         if [ -z "$MVNW_USERNAME" ] || [ -z "$MVNW_PASSWORD" ]; then
217 |             wget $QUIET "$wrapperUrl" -O "$wrapperJarPath" || rm -f "$wrapperJarPath"
218 |         else
219 |             wget $QUIET --http-user="$MVNW_USERNAME" --http-password="$MVNW_PASSWORD" "$wrapperUrl" -O "$wrapperJarPath" || rm -f "$wrapperJarPath"
220 |         fi
221 |     elif command -v curl > /dev/null; then
222 |         log "Found curl ... using curl"
223 |         [ "$MVNW_VERBOSE" = true ] && QUIET="" || QUIET="--silent"
224 |         if [ -z "$MVNW_USERNAME" ] || [ -z "$MVNW_PASSWORD" ]; then
225 |             curl $QUIET -o "$wrapperJarPath" "$wrapperUrl" -f -L || rm -f "$wrapperJarPath"
226 |         else
227 |             curl $QUIET --user "$MVNW_USERNAME:$MVNW_PASSWORD" -o "$wrapperJarPath" "$wrapperUrl" -f -L || rm -f "$wrapperJarPath"
228 |         fi
229 |     else
230 |         log "Falling back to using Java to download"
231 |         javaSource="$MAVEN_PROJECTBASEDIR/.mvn/wrapper/MavenWrapperDownloader.java"
232 |         javaClass="$MAVEN_PROJECTBASEDIR/.mvn/wrapper/MavenWrapperDownloader.class"
233 |         # For Cygwin, switch paths to Windows format before running javac
234 |         if $cygwin; then
235 |           javaSource=$(cygpath --path --windows "$javaSource")
236 |           javaClass=$(cygpath --path --windows "$javaClass")
237 |         fi
238 |         if [ -e "$javaSource" ]; then
239 |             if [ ! -e "$javaClass" ]; then
240 |                 log " - Compiling MavenWrapperDownloader.java ..."
241 |                 ("$JAVA_HOME/bin/javac" "$javaSource")
242 |             fi
243 |             if [ -e "$javaClass" ]; then
244 |                 log " - Running MavenWrapperDownloader.java ..."
245 |                 ("$JAVA_HOME/bin/java" -cp .mvn/wrapper MavenWrapperDownloader "$wrapperUrl" "$wrapperJarPath") || rm -f "$wrapperJarPath"
246 |             fi
247 |         fi
248 |     fi
249 | fi
250 | ##########################################################################################
251 | # End of extension
252 | ##########################################################################################
253 | 
254 | # If specified, validate the SHA-256 sum of the Maven wrapper jar file
255 | wrapperSha256Sum=""
256 | while IFS="=" read -r key value; do
257 |   case "$key" in (wrapperSha256Sum) wrapperSha256Sum=$value; break ;;
258 |   esac
259 | done < "$MAVEN_PROJECTBASEDIR/.mvn/wrapper/maven-wrapper.properties"
260 | if [ -n "$wrapperSha256Sum" ]; then
261 |   wrapperSha256Result=false
262 |   if command -v sha256sum > /dev/null; then
263 |     if echo "$wrapperSha256Sum  $wrapperJarPath" | sha256sum -c > /dev/null 2>&1; then
264 |       wrapperSha256Result=true
265 |     fi
266 |   elif command -v shasum > /dev/null; then
267 |     if echo "$wrapperSha256Sum  $wrapperJarPath" | shasum -a 256 -c > /dev/null 2>&1; then
268 |       wrapperSha256Result=true
269 |     fi
270 |   else
271 |     echo "Checksum validation was requested but neither 'sha256sum' or 'shasum' are available."
272 |     echo "Please install either command, or disable validation by removing 'wrapperSha256Sum' from your maven-wrapper.properties."
273 |     exit 1
274 |   fi
275 |   if [ $wrapperSha256Result = false ]; then
276 |     echo "Error: Failed to validate Maven wrapper SHA-256, your Maven wrapper might be compromised." >&2
277 |     echo "Investigate or delete $wrapperJarPath to attempt a clean download." >&2
278 |     echo "If you updated your Maven version, you need to update the specified wrapperSha256Sum property." >&2
279 |     exit 1
280 |   fi
281 | fi
282 | 
283 | MAVEN_OPTS="$(concat_lines "$MAVEN_PROJECTBASEDIR/.mvn/jvm.config") $MAVEN_OPTS"
284 | 
285 | # For Cygwin, switch paths to Windows format before running java
286 | if $cygwin; then
287 |   [ -n "$JAVA_HOME" ] &&
288 |     JAVA_HOME=$(cygpath --path --windows "$JAVA_HOME")
289 |   [ -n "$CLASSPATH" ] &&
290 |     CLASSPATH=$(cygpath --path --windows "$CLASSPATH")
291 |   [ -n "$MAVEN_PROJECTBASEDIR" ] &&
292 |     MAVEN_PROJECTBASEDIR=$(cygpath --path --windows "$MAVEN_PROJECTBASEDIR")
293 | fi
294 | 
295 | # Provide a "standardized" way to retrieve the CLI args that will
296 | # work with both Windows and non-Windows executions.
297 | MAVEN_CMD_LINE_ARGS="$MAVEN_CONFIG $*"
298 | export MAVEN_CMD_LINE_ARGS
299 | 
300 | WRAPPER_LAUNCHER=org.apache.maven.wrapper.MavenWrapperMain
301 | 
302 | # shellcheck disable=SC2086 # safe args
303 | exec "$JAVACMD" \
304 |   $MAVEN_OPTS \
305 |   $MAVEN_DEBUG_OPTS \
306 |   -classpath "$MAVEN_PROJECTBASEDIR/.mvn/wrapper/maven-wrapper.jar" \
307 |   "-Dmaven.multiModuleProjectDirectory=${MAVEN_PROJECTBASEDIR}" \
308 |   ${WRAPPER_LAUNCHER} $MAVEN_CONFIG "$@"
309 | 


--------------------------------------------------------------------------------
/mvnw.cmd:
--------------------------------------------------------------------------------
  1 | @REM ----------------------------------------------------------------------------
  2 | @REM Licensed to the Apache Software Foundation (ASF) under one
  3 | @REM or more contributor license agreements.  See the NOTICE file
  4 | @REM distributed with this work for additional information
  5 | @REM regarding copyright ownership.  The ASF licenses this file
  6 | @REM to you under the Apache License, Version 2.0 (the
  7 | @REM "License"); you may not use this file except in compliance
  8 | @REM with the License.  You may obtain a copy of the License at
  9 | @REM
 10 | @REM    http://www.apache.org/licenses/LICENSE-2.0
 11 | @REM
 12 | @REM Unless required by applicable law or agreed to in writing,
 13 | @REM software distributed under the License is distributed on an
 14 | @REM "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
 15 | @REM KIND, either express or implied.  See the License for the
 16 | @REM specific language governing permissions and limitations
 17 | @REM under the License.
 18 | @REM ----------------------------------------------------------------------------
 19 | 
 20 | @REM ----------------------------------------------------------------------------
 21 | @REM Apache Maven Wrapper startup batch script, version 3.2.0
 22 | @REM
 23 | @REM Required ENV vars:
 24 | @REM JAVA_HOME - location of a JDK home dir
 25 | @REM
 26 | @REM Optional ENV vars
 27 | @REM MAVEN_BATCH_ECHO - set to 'on' to enable the echoing of the batch commands
 28 | @REM MAVEN_BATCH_PAUSE - set to 'on' to wait for a keystroke before ending
 29 | @REM MAVEN_OPTS - parameters passed to the Java VM when running Maven
 30 | @REM     e.g. to debug Maven itself, use
 31 | @REM set MAVEN_OPTS=-Xdebug -Xrunjdwp:transport=dt_socket,server=y,suspend=y,address=8000
 32 | @REM MAVEN_SKIP_RC - flag to disable loading of mavenrc files
 33 | @REM ----------------------------------------------------------------------------
 34 | 
 35 | @REM Begin all REM lines with '@' in case MAVEN_BATCH_ECHO is 'on'
 36 | @echo off
 37 | @REM set title of command window
 38 | title %0
 39 | @REM enable echoing by setting MAVEN_BATCH_ECHO to 'on'
 40 | @if "%MAVEN_BATCH_ECHO%" == "on"  echo %MAVEN_BATCH_ECHO%
 41 | 
 42 | @REM set %HOME% to equivalent of $HOME
 43 | if "%HOME%" == "" (set "HOME=%HOMEDRIVE%%HOMEPATH%")
 44 | 
 45 | @REM Execute a user defined script before this one
 46 | if not "%MAVEN_SKIP_RC%" == "" goto skipRcPre
 47 | @REM check for pre script, once with legacy .bat ending and once with .cmd ending
 48 | if exist "%USERPROFILE%\mavenrc_pre.bat" call "%USERPROFILE%\mavenrc_pre.bat" %*
 49 | if exist "%USERPROFILE%\mavenrc_pre.cmd" call "%USERPROFILE%\mavenrc_pre.cmd" %*
 50 | :skipRcPre
 51 | 
 52 | @setlocal
 53 | 
 54 | set ERROR_CODE=0
 55 | 
 56 | @REM To isolate internal variables from possible post scripts, we use another setlocal
 57 | @setlocal
 58 | 
 59 | @REM ==== START VALIDATION ====
 60 | if not "%JAVA_HOME%" == "" goto OkJHome
 61 | 
 62 | echo.
 63 | echo Error: JAVA_HOME not found in your environment. >&2
 64 | echo Please set the JAVA_HOME variable in your environment to match the >&2
 65 | echo location of your Java installation. >&2
 66 | echo.
 67 | goto error
 68 | 
 69 | :OkJHome
 70 | if exist "%JAVA_HOME%\bin\java.exe" goto init
 71 | 
 72 | echo.
 73 | echo Error: JAVA_HOME is set to an invalid directory. >&2
 74 | echo JAVA_HOME = "%JAVA_HOME%" >&2
 75 | echo Please set the JAVA_HOME variable in your environment to match the >&2
 76 | echo location of your Java installation. >&2
 77 | echo.
 78 | goto error
 79 | 
 80 | @REM ==== END VALIDATION ====
 81 | 
 82 | :init
 83 | 
 84 | @REM Find the project base dir, i.e. the directory that contains the folder ".mvn".
 85 | @REM Fallback to current working directory if not found.
 86 | 
 87 | set MAVEN_PROJECTBASEDIR=%MAVEN_BASEDIR%
 88 | IF NOT "%MAVEN_PROJECTBASEDIR%"=="" goto endDetectBaseDir
 89 | 
 90 | set EXEC_DIR=%CD%
 91 | set WDIR=%EXEC_DIR%
 92 | :findBaseDir
 93 | IF EXIST "%WDIR%"\.mvn goto baseDirFound
 94 | cd ..
 95 | IF "%WDIR%"=="%CD%" goto baseDirNotFound
 96 | set WDIR=%CD%
 97 | goto findBaseDir
 98 | 
 99 | :baseDirFound
100 | set MAVEN_PROJECTBASEDIR=%WDIR%
101 | cd "%EXEC_DIR%"
102 | goto endDetectBaseDir
103 | 
104 | :baseDirNotFound
105 | set MAVEN_PROJECTBASEDIR=%EXEC_DIR%
106 | cd "%EXEC_DIR%"
107 | 
108 | :endDetectBaseDir
109 | 
110 | IF NOT EXIST "%MAVEN_PROJECTBASEDIR%\.mvn\jvm.config" goto endReadAdditionalConfig
111 | 
112 | @setlocal EnableExtensions EnableDelayedExpansion
113 | for /F "usebackq delims=" %%a in ("%MAVEN_PROJECTBASEDIR%\.mvn\jvm.config") do set JVM_CONFIG_MAVEN_PROPS=!JVM_CONFIG_MAVEN_PROPS! %%a
114 | @endlocal & set JVM_CONFIG_MAVEN_PROPS=%JVM_CONFIG_MAVEN_PROPS%
115 | 
116 | :endReadAdditionalConfig
117 | 
118 | SET MAVEN_JAVA_EXE="%JAVA_HOME%\bin\java.exe"
119 | set WRAPPER_JAR="%MAVEN_PROJECTBASEDIR%\.mvn\wrapper\maven-wrapper.jar"
120 | set WRAPPER_LAUNCHER=org.apache.maven.wrapper.MavenWrapperMain
121 | 
122 | set WRAPPER_URL="https://repo.maven.apache.org/maven2/org/apache/maven/wrapper/maven-wrapper/3.2.0/maven-wrapper-3.2.0.jar"
123 | 
124 | FOR /F "usebackq tokens=1,2 delims==" %%A IN ("%MAVEN_PROJECTBASEDIR%\.mvn\wrapper\maven-wrapper.properties") DO (
125 |     IF "%%A"=="wrapperUrl" SET WRAPPER_URL=%%B
126 | )
127 | 
128 | @REM Extension to allow automatically downloading the maven-wrapper.jar from Maven-central
129 | @REM This allows using the maven wrapper in projects that prohibit checking in binary data.
130 | if exist %WRAPPER_JAR% (
131 |     if "%MVNW_VERBOSE%" == "true" (
132 |         echo Found %WRAPPER_JAR%
133 |     )
134 | ) else (
135 |     if not "%MVNW_REPOURL%" == "" (
136 |         SET WRAPPER_URL="%MVNW_REPOURL%/org/apache/maven/wrapper/maven-wrapper/3.2.0/maven-wrapper-3.2.0.jar"
137 |     )
138 |     if "%MVNW_VERBOSE%" == "true" (
139 |         echo Couldn't find %WRAPPER_JAR%, downloading it ...
140 |         echo Downloading from: %WRAPPER_URL%
141 |     )
142 | 
143 |     powershell -Command "&{"^
144 | 		"$webclient = new-object System.Net.WebClient;"^
145 | 		"if (-not ([string]::IsNullOrEmpty('%MVNW_USERNAME%') -and [string]::IsNullOrEmpty('%MVNW_PASSWORD%'))) {"^
146 | 		"$webclient.Credentials = new-object System.Net.NetworkCredential('%MVNW_USERNAME%', '%MVNW_PASSWORD%');"^
147 | 		"}"^
148 | 		"[Net.ServicePointManager]::SecurityProtocol = [Net.SecurityProtocolType]::Tls12; $webclient.DownloadFile('%WRAPPER_URL%', '%WRAPPER_JAR%')"^
149 | 		"}"
150 |     if "%MVNW_VERBOSE%" == "true" (
151 |         echo Finished downloading %WRAPPER_JAR%
152 |     )
153 | )
154 | @REM End of extension
155 | 
156 | @REM If specified, validate the SHA-256 sum of the Maven wrapper jar file
157 | SET WRAPPER_SHA_256_SUM=""
158 | FOR /F "usebackq tokens=1,2 delims==" %%A IN ("%MAVEN_PROJECTBASEDIR%\.mvn\wrapper\maven-wrapper.properties") DO (
159 |     IF "%%A"=="wrapperSha256Sum" SET WRAPPER_SHA_256_SUM=%%B
160 | )
161 | IF NOT %WRAPPER_SHA_256_SUM%=="" (
162 |     powershell -Command "&{"^
163 |        "$hash = (Get-FileHash \"%WRAPPER_JAR%\" -Algorithm SHA256).Hash.ToLower();"^
164 |        "If('%WRAPPER_SHA_256_SUM%' -ne $hash){"^
165 |        "  Write-Output 'Error: Failed to validate Maven wrapper SHA-256, your Maven wrapper might be compromised.';"^
166 |        "  Write-Output 'Investigate or delete %WRAPPER_JAR% to attempt a clean download.';"^
167 |        "  Write-Output 'If you updated your Maven version, you need to update the specified wrapperSha256Sum property.';"^
168 |        "  exit 1;"^
169 |        "}"^
170 |        "}"
171 |     if ERRORLEVEL 1 goto error
172 | )
173 | 
174 | @REM Provide a "standardized" way to retrieve the CLI args that will
175 | @REM work with both Windows and non-Windows executions.
176 | set MAVEN_CMD_LINE_ARGS=%*
177 | 
178 | %MAVEN_JAVA_EXE% ^
179 |   %JVM_CONFIG_MAVEN_PROPS% ^
180 |   %MAVEN_OPTS% ^
181 |   %MAVEN_DEBUG_OPTS% ^
182 |   -classpath %WRAPPER_JAR% ^
183 |   "-Dmaven.multiModuleProjectDirectory=%MAVEN_PROJECTBASEDIR%" ^
184 |   %WRAPPER_LAUNCHER% %MAVEN_CONFIG% %*
185 | if ERRORLEVEL 1 goto error
186 | goto end
187 | 
188 | :error
189 | set ERROR_CODE=1
190 | 
191 | :end
192 | @endlocal & set ERROR_CODE=%ERROR_CODE%
193 | 
194 | if not "%MAVEN_SKIP_RC%"=="" goto skipRcPost
195 | @REM check for post script, once with legacy .bat ending and once with .cmd ending
196 | if exist "%USERPROFILE%\mavenrc_post.bat" call "%USERPROFILE%\mavenrc_post.bat"
197 | if exist "%USERPROFILE%\mavenrc_post.cmd" call "%USERPROFILE%\mavenrc_post.cmd"
198 | :skipRcPost
199 | 
200 | @REM pause the script if MAVEN_BATCH_PAUSE is set to 'on'
201 | if "%MAVEN_BATCH_PAUSE%"=="on" pause
202 | 
203 | if "%MAVEN_TERMINATE_CMD%"=="on" exit %ERROR_CODE%
204 | 
205 | cmd /C exit /B %ERROR_CODE%
206 | 


--------------------------------------------------------------------------------
/pom.xml:
--------------------------------------------------------------------------------
  1 | <?xml version="1.0" encoding="UTF-8"?>
  2 | <!--
  3 | 
  4 |      Copyright 2023 The original authors
  5 | 
  6 |      Licensed under the Apache License, Version 2.0 (the "License");
  7 |      you may not use this file except in compliance with the License.
  8 |      You may obtain a copy of the License at
  9 | 
 10 |          http://www.apache.org/licenses/LICENSE-2.0
 11 | 
 12 |      Unless required by applicable law or agreed to in writing, software
 13 |      distributed under the License is distributed on an "AS IS" BASIS,
 14 |      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 15 |      See the License for the specific language governing permissions and
 16 |      limitations under the License.
 17 | 
 18 | -->
 19 | <project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 https://maven.apache.org/xsd/maven-4.0.0.xsd">
 20 |   <modelVersion>4.0.0</modelVersion>
 21 |   
 22 |   <groupId>dev.morling.demos</groupId>
 23 |   <artifactId>average</artifactId>
 24 |   <version>1.0.0-SNAPSHOT</version>
 25 |   
 26 |   <properties>
 27 |     <maven.compiler.parameters>true</maven.compiler.parameters>
 28 |     <maven.compiler.release>21</maven.compiler.release>
 29 |     <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
 30 |     <project.reporting.outputEncoding>UTF-8</project.reporting.outputEncoding>
 31 |   </properties>
 32 | 
 33 |   <name>My OSS Project</name>
 34 |   <description>My Latest OSS Project</description>
 35 |   <inceptionYear>2021</inceptionYear>
 36 |   <url>tbd.</url>
 37 | 
 38 |   <licenses>
 39 |     <license>
 40 |       <name>Apache-2.0</name>
 41 |       <url>http://www.apache.org/licenses/LICENSE-2.0.txt</url>
 42 |       <distribution>repo</distribution>
 43 |     </license>
 44 |   </licenses>
 45 | 
 46 |   <dependencyManagement>
 47 |     <dependencies>
 48 |       <dependency>
 49 |         <groupId>org.junit</groupId>
 50 |         <artifactId>junit-bom</artifactId>
 51 |         <version>5.8.1</version>
 52 |         <type>pom</type>
 53 |         <scope>import</scope>
 54 |       </dependency>
 55 |     </dependencies>
 56 |   </dependencyManagement>
 57 | 
 58 |   <dependencies>
 59 |     <dependency>
 60 |       <groupId>org.junit.jupiter</groupId>
 61 |       <artifactId>junit-jupiter</artifactId>
 62 |       <scope>test</scope>
 63 |     </dependency>
 64 |     <dependency>
 65 |       <groupId>org.assertj</groupId>
 66 |       <artifactId>assertj-core</artifactId>
 67 |       <version>3.21.0</version>
 68 |       <scope>test</scope>
 69 |     </dependency>
 70 |   </dependencies>
 71 | 
 72 |   <build>
 73 |     <!-- Keep alphabetic order -->
 74 |     <pluginManagement>
 75 |       <plugins>
 76 |         <plugin>
 77 |           <groupId>com.mycila</groupId>
 78 |           <artifactId>license-maven-plugin</artifactId>
 79 |           <version>4.1</version>
 80 |         </plugin>
 81 |         <plugin>
 82 |           <groupId>net.revelc.code.formatter</groupId>
 83 |           <artifactId>formatter-maven-plugin</artifactId>
 84 |           <version>2.16.0</version>
 85 |           <configuration>
 86 |               <configFile>etc/eclipse-formatter-config.xml</configFile>
 87 |           </configuration>
 88 |         </plugin>
 89 |         <plugin>
 90 |           <groupId>net.revelc.code</groupId>
 91 |           <artifactId>impsort-maven-plugin</artifactId>
 92 |           <version>1.9.0</version>
 93 |           <configuration>
 94 |             <groups>java.,javax.,org.,com.</groups>
 95 |             <removeUnused>true</removeUnused>
 96 |             <staticAfter>true</staticAfter>
 97 |           </configuration>
 98 |         </plugin>
 99 |         <plugin>
100 |           <groupId>org.apache.maven.plugins</groupId>
101 |           <artifactId>maven-compiler-plugin</artifactId>
102 |           <version>3.12.1</version>
103 |           <configuration>
104 |             <parameters>true</parameters>
105 |             <compilerArgs>
106 |               <!--
107 |                 IntelliJ does not yet support the enablePreview configuration option.
108 |                 Therefore, we use a compiler argument.
109 |                 See https://youtrack.jetbrains.com/issue/IDEA-296303
110 |               -->
111 |               <compilerArg>--enable-preview</compilerArg>
112 |               <compilerArg>--add-modules</compilerArg>
113 |               <compilerArg>java.base,jdk.incubator.vector</compilerArg>
114 |             </compilerArgs>
115 |           </configuration>
116 |         </plugin>
117 |         <plugin>
118 |           <groupId>org.apache.maven.plugins</groupId>
119 |           <artifactId>maven-clean-plugin</artifactId>
120 |           <version>3.1.0</version>
121 |         </plugin>
122 |         <plugin>
123 |           <groupId>org.apache.maven.plugins</groupId>
124 |           <artifactId>maven-deploy-plugin</artifactId>
125 |           <version>3.1.1</version>
126 |         </plugin>
127 |         <plugin>
128 |           <groupId>org.apache.maven.plugins</groupId>
129 |           <artifactId>maven-enforcer-plugin</artifactId>
130 |           <version>3.3.0</version>
131 |         </plugin>
132 |         <plugin>
133 |           <groupId>org.apache.maven.plugins</groupId>
134 |           <artifactId>maven-install-plugin</artifactId>
135 |           <version>3.1.1</version>
136 |         </plugin>
137 |         <plugin>
138 |           <groupId>org.apache.maven.plugins</groupId>
139 |           <artifactId>maven-jar-plugin</artifactId>
140 |           <version>3.2.0</version>
141 |         </plugin>
142 |         <plugin>
143 |           <groupId>org.apache.maven.plugins</groupId>
144 |           <artifactId>maven-resources-plugin</artifactId>
145 |           <version>3.2.0</version>
146 |         </plugin>
147 |         <plugin>
148 |           <groupId>org.apache.maven.plugins</groupId>
149 |           <artifactId>maven-site-plugin</artifactId>
150 |           <version>3.12.1</version>
151 |         </plugin>
152 |         <plugin>
153 |           <groupId>org.apache.maven.plugins</groupId>
154 |           <artifactId>maven-surefire-plugin</artifactId>
155 |           <version>3.2.3</version>
156 |         </plugin>
157 |         <plugin>
158 |           <groupId>org.apache.maven.plugins</groupId>
159 |           <artifactId>maven-wrapper-plugin</artifactId>
160 |           <version>3.2.0</version>
161 |         </plugin>
162 |       </plugins>
163 |     </pluginManagement>
164 | 
165 |   </build>
166 |   <profiles>
167 |     <profile>
168 |       <id>ci</id>
169 |       <build>
170 |         <plugins>
171 |           <plugin>
172 |             <groupId>net.revelc.code.formatter</groupId>
173 |             <artifactId>formatter-maven-plugin</artifactId>
174 |             <executions>
175 |               <execution>
176 |                 <id>validate-format</id>
177 |                 <goals>
178 |                   <goal>validate</goal>
179 |                 </goals>
180 |                 <phase>validate</phase>
181 |               </execution>
182 |             </executions>
183 |           </plugin>
184 |         </plugins>
185 |       </build>
186 |     </profile>
187 |     <profile>
188 |       <id>qa</id>
189 |       <activation>
190 |         <property>
191 |           <name>!quick</name>
192 |         </property>
193 |       </activation>
194 |       <build>
195 |         <plugins>
196 |           <plugin>
197 |             <groupId>com.mycila</groupId>
198 |             <artifactId>license-maven-plugin</artifactId>
199 |             <configuration>
200 |               <header>etc/license.txt</header>
201 |               <strictCheck>true</strictCheck>
202 |               <aggregate>true</aggregate>
203 |               <excludes>
204 |                 <exclude>LICENSE.txt</exclude>
205 |                 <exclude>**/.dontdelete</exclude>
206 |                 <exclude>**/measurements*.txt</exclude>
207 |                 <exclude>**/measurements*.out</exclude>
208 |                 <exclude>out_expected.txt</exclude>
209 |               </excludes>
210 |             </configuration>
211 |             <executions>
212 |               <execution>
213 |                 <goals>
214 |                   <goal>check</goal>
215 |                 </goals>
216 |               </execution>
217 |             </executions>
218 |           </plugin>
219 |           <plugin>
220 |             <groupId>net.revelc.code.formatter</groupId>
221 |             <artifactId>formatter-maven-plugin</artifactId>
222 |             <executions>
223 |               <execution>
224 |                 <id>format</id>
225 |                 <goals>
226 |                   <goal>format</goal>
227 |                 </goals>
228 |                 <phase>process-sources</phase>
229 |               </execution>
230 |             </executions>
231 |           </plugin>
232 | <!--          <plugin>-->
233 | <!--            <groupId>net.revelc.code</groupId>-->
234 | <!--            <artifactId>impsort-maven-plugin</artifactId>-->
235 | <!--            <executions>-->
236 | <!--              <execution>-->
237 | <!--                <id>sort-imports</id>-->
238 | <!--                <goals>-->
239 | <!--                  <goal>sort</goal>-->
240 | <!--                </goals>-->
241 | <!--                <phase>process-sources</phase>-->
242 | <!--              </execution>-->
243 | <!--            </executions>-->
244 | <!--          </plugin>-->
245 |           <plugin>
246 |             <groupId>org.apache.maven.plugins</groupId>
247 |             <artifactId>maven-enforcer-plugin</artifactId>
248 |             <executions>
249 |               <execution>
250 |                 <id>enforce-plugin-versions</id>
251 |                 <goals>
252 |                   <goal>enforce</goal>
253 |                 </goals>
254 |                 <configuration>
255 |                   <rules>
256 |                     <requireJavaVersion>
257 |                       <version>${maven.compiler.release}</version>
258 |                     </requireJavaVersion>
259 |                     <requirePluginVersions>
260 |                        <banLatest>true</banLatest>
261 |                        <banRelease>true</banRelease>
262 |                        <banSnapshots>true</banSnapshots>
263 |                        <phases>clean,deploy,site</phases>
264 |                     </requirePluginVersions>
265 |                   </rules>
266 |                 </configuration>
267 |               </execution>
268 |             </executions>
269 |           </plugin>
270 |         </plugins>
271 |       </build>
272 |     </profile>
273 |     <profile>
274 |       <id>quick</id>
275 |       <activation>
276 |         <property>
277 |           <name>quick</name>
278 |         </property>
279 |       </activation>
280 |       <properties>
281 |         <skipTests>true</skipTests>
282 |       </properties>
283 |     </profile>
284 |   </profiles>
285 | </project>
286 | 


--------------------------------------------------------------------------------
/prepare.sh:
--------------------------------------------------------------------------------
 1 | #!/bin/sh
 2 | #
 3 | #  Copyright 2023 The original authors
 4 | #
 5 | #  Licensed under the Apache License, Version 2.0 (the "License");
 6 | #  you may not use this file except in compliance with the License.
 7 | #  You may obtain a copy of the License at
 8 | #
 9 | #      http://www.apache.org/licenses/LICENSE-2.0
10 | #
11 | #  Unless required by applicable law or agreed to in writing, software
12 | #  distributed under the License is distributed on an "AS IS" BASIS,
13 | #  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
14 | #  See the License for the specific language governing permissions and
15 | #  limitations under the License.
16 | #
17 | 
18 | set -x
19 | 
20 | if [ -z "$1" ]
21 |   then
22 |     echo "Usage: prepare.sh <fork name>:<branch name>"
23 |     exit 1
24 | fi
25 | 
26 | parts=(${1//:/ })
27 | echo "  User: ${parts[0]}"
28 | echo "Branch: ${parts[1]}"
29 | 
30 | git branch -D ${parts[0]} &>/dev/null
31 | 
32 | git checkout -b ${parts[0]}
33 | git fetch https://github.com/${parts[0]}/1brc.git ${parts[1]}
34 | # git fetch git@github.com:${parts[0]}/1brc.git ${parts[1]}
35 | git reset --hard FETCH_HEAD
36 | git rebase main
37 | 


--------------------------------------------------------------------------------
/process.sh:
--------------------------------------------------------------------------------
 1 | #!/bin/sh
 2 | #
 3 | #  Copyright 2023 The original authors
 4 | #
 5 | #  Licensed under the Apache License, Version 2.0 (the "License");
 6 | #  you may not use this file except in compliance with the License.
 7 | #  You may obtain a copy of the License at
 8 | #
 9 | #      http://www.apache.org/licenses/LICENSE-2.0
10 | #
11 | #  Unless required by applicable law or agreed to in writing, software
12 | #  distributed under the License is distributed on an "AS IS" BASIS,
13 | #  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
14 | #  See the License for the specific language governing permissions and
15 | #  limitations under the License.
16 | #
17 | 
18 | if [ -z "$1" ]
19 |   then
20 |     echo "Usage: process_output.sh <fork name>"
21 |     exit 1
22 | fi
23 | 
24 | java --enable-preview --source=21 process_output.java out_expected.txt $1.out
25 | 


--------------------------------------------------------------------------------
/process_output.java:
--------------------------------------------------------------------------------
 1 | /*
 2 |  *  Copyright 2023 The original authors
 3 |  *
 4 |  *  Licensed under the Apache License, Version 2.0 (the "License");
 5 |  *  you may not use this file except in compliance with the License.
 6 |  *  You may obtain a copy of the License at
 7 |  *
 8 |  *      http://www.apache.org/licenses/LICENSE-2.0
 9 |  *
10 |  *  Unless required by applicable law or agreed to in writing, software
11 |  *  distributed under the License is distributed on an "AS IS" BASIS,
12 |  *  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
13 |  *  See the License for the specific language governing permissions and
14 |  *  limitations under the License.
15 |  */
16 | 
17 | import java.nio.file.Files;
18 | import java.nio.file.Paths;
19 | import java.util.ArrayList;
20 | import java.util.Comparator;
21 | import java.util.List;
22 | import java.util.stream.Collectors;
23 | import java.time.Duration;
24 | 
25 | public class process_output {
26 | 
27 |     public static void main(String... args) throws Exception {
28 |         String expectedFile = args[0];
29 |         String actualFile = args[1];
30 | 
31 |         String expected = new String(Files.readAllBytes(Paths.get(expectedFile)));
32 |         List<String> times = new ArrayList<>();
33 | 
34 |         var outputLines = Files.lines(Paths.get(actualFile))
35 |                 .collect(Collectors.toList());
36 | 
37 |         int matched = 0;
38 | 
39 |         for (String line : outputLines) {
40 |             if (line.contains("Hamburg")) {
41 |                 if (!line.equals(expected)) {
42 |                     System.err.println("FAILURE Unexpected output");
43 |                     System.err.println(line);
44 |                 }
45 |                 else {
46 |                     matched++;
47 |                 }
48 |             }
49 |             else if (line.startsWith("real")) {
50 |                 times.add(line);
51 |             }
52 |         }
53 | 
54 |         if (matched == 5) {
55 |             System.out.println("OK Output matched");
56 |         }
57 |         else {
58 |             System.err.println("FAILURE Output didn't match");
59 |         }
60 | 
61 |         System.out.println();
62 |         System.out.println(actualFile);
63 | 
64 |         System.out.println(times.stream()
65 |             .map(t -> t.substring(5))
66 |             .map(t -> t.replace("s", "").replace("m", ":"))
67 |             .collect(Collectors.joining(System.lineSeparator())));
68 | 
69 |         var asDurations = times.stream()
70 |             .map(t -> t.substring(5))
71 |             .map(t -> t.replace("s", "S").replace("m", "M"))
72 |             .map(t -> "PT" + t)
73 |             .map(Duration::parse)
74 |             .collect(Collectors.toList());
75 | 
76 |         var min = asDurations.stream().min(Comparator.naturalOrder()).get();
77 |         var max = asDurations.stream().max(Comparator.naturalOrder()).get();
78 | 
79 |         var evaluated = asDurations.stream()
80 |             .filter(d -> d != min && d != max)
81 |             .collect(Collectors.toList());
82 | 
83 |         var mean = evaluated.get(0).plus(evaluated.get(1)).plus(evaluated.get(2)).dividedBy(3);
84 |         var result = String.format("%02d:%02d.%.0f", mean.toMinutesPart(), mean.toSecondsPart(), (double) mean.toNanosPart() / 1_000_000);
85 |         var author = actualFile.replace(".out", "");
86 | 
87 |         System.out.println(String.format("\n|   |        %s| [link](https://github.com/gunnarmorling/1brc/blob/main/src/main/java/dev/morling/onebrc/CalculateAverage_%s.java)| 21.0.1-open | [%s](https://github.com/%s)|", result, author, author, author));
88 |     }
89 | }
90 | 


--------------------------------------------------------------------------------
/src/main/java/dev/morling/onebrc/CalculateAverage.java:
--------------------------------------------------------------------------------
 1 | /*
 2 |  *  Copyright 2023 The original authors
 3 |  *
 4 |  *  Licensed under the Apache License, Version 2.0 (the "License");
 5 |  *  you may not use this file except in compliance with the License.
 6 |  *  You may obtain a copy of the License at
 7 |  *
 8 |  *      http://www.apache.org/licenses/LICENSE-2.0
 9 |  *
10 |  *  Unless required by applicable law or agreed to in writing, software
11 |  *  distributed under the License is distributed on an "AS IS" BASIS,
12 |  *  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
13 |  *  See the License for the specific language governing permissions and
14 |  *  limitations under the License.
15 |  */
16 | package dev.morling.onebrc;
17 | 
18 | import static java.util.stream.Collectors.*;
19 | 
20 | import java.io.IOException;
21 | import java.nio.file.Files;
22 | import java.nio.file.Paths;
23 | import java.util.Map;
24 | import java.util.TreeMap;
25 | import java.util.stream.Collector;
26 | 
27 | public class CalculateAverage {
28 | 
29 |     private static final String FILE = "./measurements.txt";
30 | 
31 |     private static record Measurement(String station, double value) {
32 |         private Measurement(String[] parts) {
33 |             this(parts[0], Double.parseDouble(parts[1]));
34 |         }
35 |     }
36 | 
37 |     private static record ResultRow(double min, double mean, double max) {
38 |         public String toString() {
39 |             return round(min) + "/" + round(mean) + "/" + round(max);
40 |         }
41 | 
42 |         private double round(double value) {
43 |             return Math.round(value * 10.0) / 10.0;
44 |         }
45 |     };
46 | 
47 |     private static class MeasurementAggregator {
48 |         private double min = Double.POSITIVE_INFINITY;
49 |         private double max = Double.NEGATIVE_INFINITY;
50 |         private double sum;
51 |         private long count;
52 |     }
53 | 
54 |     public static void main(String[] args) throws IOException {
55 |         // Map<String, Double> measurements1 = Files.lines(Paths.get(FILE))
56 |         // .map(l -> l.split(";"))
57 |         // .collect(groupingBy(m -> m[0], averagingDouble(m -> Double.parseDouble(m[1]))));
58 |         //
59 |         // measurements1 = new TreeMap<>(measurements1.entrySet()
60 |         // .stream()
61 |         // .collect(toMap(e -> e.getKey(), e -> Math.round(e.getValue() * 10.0) / 10.0)));
62 |         // System.out.println(measurements1);
63 | 
64 |         Collector<Measurement, MeasurementAggregator, ResultRow> collector = Collector.of(
65 |                 MeasurementAggregator::new,
66 |                 (a, m) -> {
67 |                     a.min = Math.min(a.min, m.value);
68 |                     a.max = Math.max(a.max, m.value);
69 |                     a.sum += m.value;
70 |                     a.count++;
71 |                 },
72 |                 (agg1, agg2) -> {
73 |                     var res = new MeasurementAggregator();
74 |                     res.min = Math.min(agg1.min, agg2.min);
75 |                     res.max = Math.max(agg1.max, agg2.max);
76 |                     res.sum = agg1.sum + agg2.sum;
77 |                     res.count = agg1.count + agg2.count;
78 | 
79 |                     return res;
80 |                 },
81 |                 agg -> {
82 |                     return new ResultRow(agg.min, agg.sum / agg.count, agg.max);
83 |                 });
84 | 
85 |         Map<String, ResultRow> measurements = new TreeMap<>(Files.lines(Paths.get(FILE))
86 |                 .map(l -> new Measurement(l.split(";")))
87 |                 .collect(groupingBy(m -> m.station(), collector)));
88 | 
89 |         System.out.println(measurements);
90 |     }
91 | }
92 | 


--------------------------------------------------------------------------------
/src/main/java/dev/morling/onebrc/CreateMeasurements.java:
--------------------------------------------------------------------------------
  1 | /*
  2 |  *  Copyright 2023 The original authors
  3 |  *
  4 |  *  Licensed under the Apache License, Version 2.0 (the "License");
  5 |  *  you may not use this file except in compliance with the License.
  6 |  *  You may obtain a copy of the License at
  7 |  *
  8 |  *      http://www.apache.org/licenses/LICENSE-2.0
  9 |  *
 10 |  *  Unless required by applicable law or agreed to in writing, software
 11 |  *  distributed under the License is distributed on an "AS IS" BASIS,
 12 |  *  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 13 |  *  See the License for the specific language governing permissions and
 14 |  *  limitations under the License.
 15 |  */
 16 | package dev.morling.onebrc;
 17 | 
 18 | import java.io.BufferedWriter;
 19 | import java.nio.file.Files;
 20 | import java.nio.file.Path;
 21 | import java.util.List;
 22 | import java.util.concurrent.ThreadLocalRandom;
 23 | 
 24 | public class CreateMeasurements {
 25 | 
 26 |     private static final Path MEASUREMENT_FILE = Path.of("./measurements.txt");
 27 | 
 28 |     private record WeatherStation(String id, double meanTemperature) {
 29 |         double measurement() {
 30 |             double m = ThreadLocalRandom.current().nextGaussian(meanTemperature, 10);
 31 |             return Math.round(m * 10.0) / 10.0;
 32 |         }
 33 |     }
 34 | 
 35 |     public static void main(String[] args) throws Exception {
 36 |         long start = System.currentTimeMillis();
 37 | 
 38 |         if (args.length != 1) {
 39 |             System.out.println("Usage: create_measurements.sh <number of records to create>");
 40 |             System.exit(1);
 41 |         }
 42 | 
 43 |         int size = 0;
 44 |         try {
 45 |             size = Integer.parseInt(args[0]);
 46 |         }
 47 |         catch (NumberFormatException e) {
 48 |             System.out.println("Invalid value for <number of records to create>");
 49 |             System.out.println("Usage: CreateMeasurements <number of records to create>");
 50 |             System.exit(1);
 51 |         }
 52 | 
 53 |         // @formatter:off
 54 |         // data from https://en.wikipedia.org/wiki/List_of_cities_by_average_temperature;
 55 |         // converted using https://wikitable2csv.ggor.de/
 56 |         // brought to form using DuckDB:
 57 |         // D copy (
 58 |         //     select City, regexp_extract(Year,'(.*)\n.*', 1) as AverageTemp
 59 |         //     from (
 60 |         //         select City,Year
 61 |         //         from read_csv_auto('List_of_cities_by_average_temperature_1.csv', header = true)
 62 |         //         union
 63 |         //         select City,Year
 64 |         //         from read_csv_auto('List_of_cities_by_average_temperature_2.csv', header = true)
 65 |         //         union
 66 |         //         select City,Year
 67 |         //         from read_csv_auto('List_of_cities_by_average_temperature_3.csv', header = true)
 68 |         //         union
 69 |         //         select City,Year
 70 |         //         from read_csv_auto('List_of_cities_by_average_temperature_4.csv', header = true)
 71 |         //         union
 72 |         //         select City,Year
 73 |         //         from read_csv_auto('List_of_cities_by_average_temperature_5.csv', header = true)
 74 |         //         )
 75 |         // ) TO 'output.csv' (HEADER, DELIMITER ',');
 76 |         // @formatter:on
 77 |         List<WeatherStation> stations = List.of(
 78 |                 new WeatherStation("Abha", 18.0),
 79 |                 new WeatherStation("Abidjan", 26.0),
 80 |                 new WeatherStation("Abéché", 29.4),
 81 |                 new WeatherStation("Accra", 26.4),
 82 |                 new WeatherStation("Addis Ababa", 16.0),
 83 |                 new WeatherStation("Adelaide", 17.3),
 84 |                 new WeatherStation("Aden", 29.1),
 85 |                 new WeatherStation("Ahvaz", 25.4),
 86 |                 new WeatherStation("Albuquerque", 14.0),
 87 |                 new WeatherStation("Alexandra", 11.0),
 88 |                 new WeatherStation("Alexandria", 20.0),
 89 |                 new WeatherStation("Algiers", 18.2),
 90 |                 new WeatherStation("Alice Springs", 21.0),
 91 |                 new WeatherStation("Almaty", 10.0),
 92 |                 new WeatherStation("Amsterdam", 10.2),
 93 |                 new WeatherStation("Anadyr", -6.9),
 94 |                 new WeatherStation("Anchorage", 2.8),
 95 |                 new WeatherStation("Andorra la Vella", 9.8),
 96 |                 new WeatherStation("Ankara", 12.0),
 97 |                 new WeatherStation("Antananarivo", 17.9),
 98 |                 new WeatherStation("Antsiranana", 25.2),
 99 |                 new WeatherStation("Arkhangelsk", 1.3),
100 |                 new WeatherStation("Ashgabat", 17.1),
101 |                 new WeatherStation("Asmara", 15.6),
102 |                 new WeatherStation("Assab", 30.5),
103 |                 new WeatherStation("Astana", 3.5),
104 |                 new WeatherStation("Athens", 19.2),
105 |                 new WeatherStation("Atlanta", 17.0),
106 |                 new WeatherStation("Auckland", 15.2),
107 |                 new WeatherStation("Austin", 20.7),
108 |                 new WeatherStation("Baghdad", 22.77),
109 |                 new WeatherStation("Baguio", 19.5),
110 |                 new WeatherStation("Baku", 15.1),
111 |                 new WeatherStation("Baltimore", 13.1),
112 |                 new WeatherStation("Bamako", 27.8),
113 |                 new WeatherStation("Bangkok", 28.6),
114 |                 new WeatherStation("Bangui", 26.0),
115 |                 new WeatherStation("Banjul", 26.0),
116 |                 new WeatherStation("Barcelona", 18.2),
117 |                 new WeatherStation("Bata", 25.1),
118 |                 new WeatherStation("Batumi", 14.0),
119 |                 new WeatherStation("Beijing", 12.9),
120 |                 new WeatherStation("Beirut", 20.9),
121 |                 new WeatherStation("Belgrade", 12.5),
122 |                 new WeatherStation("Belize City", 26.7),
123 |                 new WeatherStation("Benghazi", 19.9),
124 |                 new WeatherStation("Bergen", 7.7),
125 |                 new WeatherStation("Berlin", 10.3),
126 |                 new WeatherStation("Bilbao", 14.7),
127 |                 new WeatherStation("Birao", 26.5),
128 |                 new WeatherStation("Bishkek", 11.3),
129 |                 new WeatherStation("Bissau", 27.0),
130 |                 new WeatherStation("Blantyre", 22.2),
131 |                 new WeatherStation("Bloemfontein", 15.6),
132 |                 new WeatherStation("Boise", 11.4),
133 |                 new WeatherStation("Bordeaux", 14.2),
134 |                 new WeatherStation("Bosaso", 30.0),
135 |                 new WeatherStation("Boston", 10.9),
136 |                 new WeatherStation("Bouaké", 26.0),
137 |                 new WeatherStation("Bratislava", 10.5),
138 |                 new WeatherStation("Brazzaville", 25.0),
139 |                 new WeatherStation("Bridgetown", 27.0),
140 |                 new WeatherStation("Brisbane", 21.4),
141 |                 new WeatherStation("Brussels", 10.5),
142 |                 new WeatherStation("Bucharest", 10.8),
143 |                 new WeatherStation("Budapest", 11.3),
144 |                 new WeatherStation("Bujumbura", 23.8),
145 |                 new WeatherStation("Bulawayo", 18.9),
146 |                 new WeatherStation("Burnie", 13.1),
147 |                 new WeatherStation("Busan", 15.0),
148 |                 new WeatherStation("Cabo San Lucas", 23.9),
149 |                 new WeatherStation("Cairns", 25.0),
150 |                 new WeatherStation("Cairo", 21.4),
151 |                 new WeatherStation("Calgary", 4.4),
152 |                 new WeatherStation("Canberra", 13.1),
153 |                 new WeatherStation("Cape Town", 16.2),
154 |                 new WeatherStation("Changsha", 17.4),
155 |                 new WeatherStation("Charlotte", 16.1),
156 |                 new WeatherStation("Chiang Mai", 25.8),
157 |                 new WeatherStation("Chicago", 9.8),
158 |                 new WeatherStation("Chihuahua", 18.6),
159 |                 new WeatherStation("Chișinău", 10.2),
160 |                 new WeatherStation("Chittagong", 25.9),
161 |                 new WeatherStation("Chongqing", 18.6),
162 |                 new WeatherStation("Christchurch", 12.2),
163 |                 new WeatherStation("City of San Marino", 11.8),
164 |                 new WeatherStation("Colombo", 27.4),
165 |                 new WeatherStation("Columbus", 11.7),
166 |                 new WeatherStation("Conakry", 26.4),
167 |                 new WeatherStation("Copenhagen", 9.1),
168 |                 new WeatherStation("Cotonou", 27.2),
169 |                 new WeatherStation("Cracow", 9.3),
170 |                 new WeatherStation("Da Lat", 17.9),
171 |                 new WeatherStation("Da Nang", 25.8),
172 |                 new WeatherStation("Dakar", 24.0),
173 |                 new WeatherStation("Dallas", 19.0),
174 |                 new WeatherStation("Damascus", 17.0),
175 |                 new WeatherStation("Dampier", 26.4),
176 |                 new WeatherStation("Dar es Salaam", 25.8),
177 |                 new WeatherStation("Darwin", 27.6),
178 |                 new WeatherStation("Denpasar", 23.7),
179 |                 new WeatherStation("Denver", 10.4),
180 |                 new WeatherStation("Detroit", 10.0),
181 |                 new WeatherStation("Dhaka", 25.9),
182 |                 new WeatherStation("Dikson", -11.1),
183 |                 new WeatherStation("Dili", 26.6),
184 |                 new WeatherStation("Djibouti", 29.9),
185 |                 new WeatherStation("Dodoma", 22.7),
186 |                 new WeatherStation("Dolisie", 24.0),
187 |                 new WeatherStation("Douala", 26.7),
188 |                 new WeatherStation("Dubai", 26.9),
189 |                 new WeatherStation("Dublin", 9.8),
190 |                 new WeatherStation("Dunedin", 11.1),
191 |                 new WeatherStation("Durban", 20.6),
192 |                 new WeatherStation("Dushanbe", 14.7),
193 |                 new WeatherStation("Edinburgh", 9.3),
194 |                 new WeatherStation("Edmonton", 4.2),
195 |                 new WeatherStation("El Paso", 18.1),
196 |                 new WeatherStation("Entebbe", 21.0),
197 |                 new WeatherStation("Erbil", 19.5),
198 |                 new WeatherStation("Erzurum", 5.1),
199 |                 new WeatherStation("Fairbanks", -2.3),
200 |                 new WeatherStation("Fianarantsoa", 17.9),
201 |                 new WeatherStation("Flores,  Petén", 26.4),
202 |                 new WeatherStation("Frankfurt", 10.6),
203 |                 new WeatherStation("Fresno", 17.9),
204 |                 new WeatherStation("Fukuoka", 17.0),
205 |                 new WeatherStation("Gabès", 19.5),
206 |                 new WeatherStation("Gaborone", 21.0),
207 |                 new WeatherStation("Gagnoa", 26.0),
208 |                 new WeatherStation("Gangtok", 15.2),
209 |                 new WeatherStation("Garissa", 29.3),
210 |                 new WeatherStation("Garoua", 28.3),
211 |                 new WeatherStation("George Town", 27.9),
212 |                 new WeatherStation("Ghanzi", 21.4),
213 |                 new WeatherStation("Gjoa Haven", -14.4),
214 |                 new WeatherStation("Guadalajara", 20.9),
215 |                 new WeatherStation("Guangzhou", 22.4),
216 |                 new WeatherStation("Guatemala City", 20.4),
217 |                 new WeatherStation("Halifax", 7.5),
218 |                 new WeatherStation("Hamburg", 9.7),
219 |                 new WeatherStation("Hamilton", 13.8),
220 |                 new WeatherStation("Hanga Roa", 20.5),
221 |                 new WeatherStation("Hanoi", 23.6),
222 |                 new WeatherStation("Harare", 18.4),
223 |                 new WeatherStation("Harbin", 5.0),
224 |                 new WeatherStation("Hargeisa", 21.7),
225 |                 new WeatherStation("Hat Yai", 27.0),
226 |                 new WeatherStation("Havana", 25.2),
227 |                 new WeatherStation("Helsinki", 5.9),
228 |                 new WeatherStation("Heraklion", 18.9),
229 |                 new WeatherStation("Hiroshima", 16.3),
230 |                 new WeatherStation("Ho Chi Minh City", 27.4),
231 |                 new WeatherStation("Hobart", 12.7),
232 |                 new WeatherStation("Hong Kong", 23.3),
233 |                 new WeatherStation("Honiara", 26.5),
234 |                 new WeatherStation("Honolulu", 25.4),
235 |                 new WeatherStation("Houston", 20.8),
236 |                 new WeatherStation("Ifrane", 11.4),
237 |                 new WeatherStation("Indianapolis", 11.8),
238 |                 new WeatherStation("Iqaluit", -9.3),
239 |                 new WeatherStation("Irkutsk", 1.0),
240 |                 new WeatherStation("Istanbul", 13.9),
241 |                 new WeatherStation("İzmir", 17.9),
242 |                 new WeatherStation("Jacksonville", 20.3),
243 |                 new WeatherStation("Jakarta", 26.7),
244 |                 new WeatherStation("Jayapura", 27.0),
245 |                 new WeatherStation("Jerusalem", 18.3),
246 |                 new WeatherStation("Johannesburg", 15.5),
247 |                 new WeatherStation("Jos", 22.8),
248 |                 new WeatherStation("Juba", 27.8),
249 |                 new WeatherStation("Kabul", 12.1),
250 |                 new WeatherStation("Kampala", 20.0),
251 |                 new WeatherStation("Kandi", 27.7),
252 |                 new WeatherStation("Kankan", 26.5),
253 |                 new WeatherStation("Kano", 26.4),
254 |                 new WeatherStation("Kansas City", 12.5),
255 |                 new WeatherStation("Karachi", 26.0),
256 |                 new WeatherStation("Karonga", 24.4),
257 |                 new WeatherStation("Kathmandu", 18.3),
258 |                 new WeatherStation("Khartoum", 29.9),
259 |                 new WeatherStation("Kingston", 27.4),
260 |                 new WeatherStation("Kinshasa", 25.3),
261 |                 new WeatherStation("Kolkata", 26.7),
262 |                 new WeatherStation("Kuala Lumpur", 27.3),
263 |                 new WeatherStation("Kumasi", 26.0),
264 |                 new WeatherStation("Kunming", 15.7),
265 |                 new WeatherStation("Kuopio", 3.4),
266 |                 new WeatherStation("Kuwait City", 25.7),
267 |                 new WeatherStation("Kyiv", 8.4),
268 |                 new WeatherStation("Kyoto", 15.8),
269 |                 new WeatherStation("La Ceiba", 26.2),
270 |                 new WeatherStation("La Paz", 23.7),
271 |                 new WeatherStation("Lagos", 26.8),
272 |                 new WeatherStation("Lahore", 24.3),
273 |                 new WeatherStation("Lake Havasu City", 23.7),
274 |                 new WeatherStation("Lake Tekapo", 8.7),
275 |                 new WeatherStation("Las Palmas de Gran Canaria", 21.2),
276 |                 new WeatherStation("Las Vegas", 20.3),
277 |                 new WeatherStation("Launceston", 13.1),
278 |                 new WeatherStation("Lhasa", 7.6),
279 |                 new WeatherStation("Libreville", 25.9),
280 |                 new WeatherStation("Lisbon", 17.5),
281 |                 new WeatherStation("Livingstone", 21.8),
282 |                 new WeatherStation("Ljubljana", 10.9),
283 |                 new WeatherStation("Lodwar", 29.3),
284 |                 new WeatherStation("Lomé", 26.9),
285 |                 new WeatherStation("London", 11.3),
286 |                 new WeatherStation("Los Angeles", 18.6),
287 |                 new WeatherStation("Louisville", 13.9),
288 |                 new WeatherStation("Luanda", 25.8),
289 |                 new WeatherStation("Lubumbashi", 20.8),
290 |                 new WeatherStation("Lusaka", 19.9),
291 |                 new WeatherStation("Luxembourg City", 9.3),
292 |                 new WeatherStation("Lviv", 7.8),
293 |                 new WeatherStation("Lyon", 12.5),
294 |                 new WeatherStation("Madrid", 15.0),
295 |                 new WeatherStation("Mahajanga", 26.3),
296 |                 new WeatherStation("Makassar", 26.7),
297 |                 new WeatherStation("Makurdi", 26.0),
298 |                 new WeatherStation("Malabo", 26.3),
299 |                 new WeatherStation("Malé", 28.0),
300 |                 new WeatherStation("Managua", 27.3),
301 |                 new WeatherStation("Manama", 26.5),
302 |                 new WeatherStation("Mandalay", 28.0),
303 |                 new WeatherStation("Mango", 28.1),
304 |                 new WeatherStation("Manila", 28.4),
305 |                 new WeatherStation("Maputo", 22.8),
306 |                 new WeatherStation("Marrakesh", 19.6),
307 |                 new WeatherStation("Marseille", 15.8),
308 |                 new WeatherStation("Maun", 22.4),
309 |                 new WeatherStation("Medan", 26.5),
310 |                 new WeatherStation("Mek'ele", 22.7),
311 |                 new WeatherStation("Melbourne", 15.1),
312 |                 new WeatherStation("Memphis", 17.2),
313 |                 new WeatherStation("Mexicali", 23.1),
314 |                 new WeatherStation("Mexico City", 17.5),
315 |                 new WeatherStation("Miami", 24.9),
316 |                 new WeatherStation("Milan", 13.0),
317 |                 new WeatherStation("Milwaukee", 8.9),
318 |                 new WeatherStation("Minneapolis", 7.8),
319 |                 new WeatherStation("Minsk", 6.7),
320 |                 new WeatherStation("Mogadishu", 27.1),
321 |                 new WeatherStation("Mombasa", 26.3),
322 |                 new WeatherStation("Monaco", 16.4),
323 |                 new WeatherStation("Moncton", 6.1),
324 |                 new WeatherStation("Monterrey", 22.3),
325 |                 new WeatherStation("Montreal", 6.8),
326 |                 new WeatherStation("Moscow", 5.8),
327 |                 new WeatherStation("Mumbai", 27.1),
328 |                 new WeatherStation("Murmansk", 0.6),
329 |                 new WeatherStation("Muscat", 28.0),
330 |                 new WeatherStation("Mzuzu", 17.7),
331 |                 new WeatherStation("N'Djamena", 28.3),
332 |                 new WeatherStation("Naha", 23.1),
333 |                 new WeatherStation("Nairobi", 17.8),
334 |                 new WeatherStation("Nakhon Ratchasima", 27.3),
335 |                 new WeatherStation("Napier", 14.6),
336 |                 new WeatherStation("Napoli", 15.9),
337 |                 new WeatherStation("Nashville", 15.4),
338 |                 new WeatherStation("Nassau", 24.6),
339 |                 new WeatherStation("Ndola", 20.3),
340 |                 new WeatherStation("New Delhi", 25.0),
341 |                 new WeatherStation("New Orleans", 20.7),
342 |                 new WeatherStation("New York City", 12.9),
343 |                 new WeatherStation("Ngaoundéré", 22.0),
344 |                 new WeatherStation("Niamey", 29.3),
345 |                 new WeatherStation("Nicosia", 19.7),
346 |                 new WeatherStation("Niigata", 13.9),
347 |                 new WeatherStation("Nouadhibou", 21.3),
348 |                 new WeatherStation("Nouakchott", 25.7),
349 |                 new WeatherStation("Novosibirsk", 1.7),
350 |                 new WeatherStation("Nuuk", -1.4),
351 |                 new WeatherStation("Odesa", 10.7),
352 |                 new WeatherStation("Odienné", 26.0),
353 |                 new WeatherStation("Oklahoma City", 15.9),
354 |                 new WeatherStation("Omaha", 10.6),
355 |                 new WeatherStation("Oranjestad", 28.1),
356 |                 new WeatherStation("Oslo", 5.7),
357 |                 new WeatherStation("Ottawa", 6.6),
358 |                 new WeatherStation("Ouagadougou", 28.3),
359 |                 new WeatherStation("Ouahigouya", 28.6),
360 |                 new WeatherStation("Ouarzazate", 18.9),
361 |                 new WeatherStation("Oulu", 2.7),
362 |                 new WeatherStation("Palembang", 27.3),
363 |                 new WeatherStation("Palermo", 18.5),
364 |                 new WeatherStation("Palm Springs", 24.5),
365 |                 new WeatherStation("Palmerston North", 13.2),
366 |                 new WeatherStation("Panama City", 28.0),
367 |                 new WeatherStation("Parakou", 26.8),
368 |                 new WeatherStation("Paris", 12.3),
369 |                 new WeatherStation("Perth", 18.7),
370 |                 new WeatherStation("Petropavlovsk-Kamchatsky", 1.9),
371 |                 new WeatherStation("Philadelphia", 13.2),
372 |                 new WeatherStation("Phnom Penh", 28.3),
373 |                 new WeatherStation("Phoenix", 23.9),
374 |                 new WeatherStation("Pittsburgh", 10.8),
375 |                 new WeatherStation("Podgorica", 15.3),
376 |                 new WeatherStation("Pointe-Noire", 26.1),
377 |                 new WeatherStation("Pontianak", 27.7),
378 |                 new WeatherStation("Port Moresby", 26.9),
379 |                 new WeatherStation("Port Sudan", 28.4),
380 |                 new WeatherStation("Port Vila", 24.3),
381 |                 new WeatherStation("Port-Gentil", 26.0),
382 |                 new WeatherStation("Portland (OR)", 12.4),
383 |                 new WeatherStation("Porto", 15.7),
384 |                 new WeatherStation("Prague", 8.4),
385 |                 new WeatherStation("Praia", 24.4),
386 |                 new WeatherStation("Pretoria", 18.2),
387 |                 new WeatherStation("Pyongyang", 10.8),
388 |                 new WeatherStation("Rabat", 17.2),
389 |                 new WeatherStation("Rangpur", 24.4),
390 |                 new WeatherStation("Reggane", 28.3),
391 |                 new WeatherStation("Reykjavík", 4.3),
392 |                 new WeatherStation("Riga", 6.2),
393 |                 new WeatherStation("Riyadh", 26.0),
394 |                 new WeatherStation("Rome", 15.2),
395 |                 new WeatherStation("Roseau", 26.2),
396 |                 new WeatherStation("Rostov-on-Don", 9.9),
397 |                 new WeatherStation("Sacramento", 16.3),
398 |                 new WeatherStation("Saint Petersburg", 5.8),
399 |                 new WeatherStation("Saint-Pierre", 5.7),
400 |                 new WeatherStation("Salt Lake City", 11.6),
401 |                 new WeatherStation("San Antonio", 20.8),
402 |                 new WeatherStation("San Diego", 17.8),
403 |                 new WeatherStation("San Francisco", 14.6),
404 |                 new WeatherStation("San Jose", 16.4),
405 |                 new WeatherStation("San José", 22.6),
406 |                 new WeatherStation("San Juan", 27.2),
407 |                 new WeatherStation("San Salvador", 23.1),
408 |                 new WeatherStation("Sana'a", 20.0),
409 |                 new WeatherStation("Santo Domingo", 25.9),
410 |                 new WeatherStation("Sapporo", 8.9),
411 |                 new WeatherStation("Sarajevo", 10.1),
412 |                 new WeatherStation("Saskatoon", 3.3),
413 |                 new WeatherStation("Seattle", 11.3),
414 |                 new WeatherStation("Ségou", 28.0),
415 |                 new WeatherStation("Seoul", 12.5),
416 |                 new WeatherStation("Seville", 19.2),
417 |                 new WeatherStation("Shanghai", 16.7),
418 |                 new WeatherStation("Singapore", 27.0),
419 |                 new WeatherStation("Skopje", 12.4),
420 |                 new WeatherStation("Sochi", 14.2),
421 |                 new WeatherStation("Sofia", 10.6),
422 |                 new WeatherStation("Sokoto", 28.0),
423 |                 new WeatherStation("Split", 16.1),
424 |                 new WeatherStation("St. John's", 5.0),
425 |                 new WeatherStation("St. Louis", 13.9),
426 |                 new WeatherStation("Stockholm", 6.6),
427 |                 new WeatherStation("Surabaya", 27.1),
428 |                 new WeatherStation("Suva", 25.6),
429 |                 new WeatherStation("Suwałki", 7.2),
430 |                 new WeatherStation("Sydney", 17.7),
431 |                 new WeatherStation("Tabora", 23.0),
432 |                 new WeatherStation("Tabriz", 12.6),
433 |                 new WeatherStation("Taipei", 23.0),
434 |                 new WeatherStation("Tallinn", 6.4),
435 |                 new WeatherStation("Tamale", 27.9),
436 |                 new WeatherStation("Tamanrasset", 21.7),
437 |                 new WeatherStation("Tampa", 22.9),
438 |                 new WeatherStation("Tashkent", 14.8),
439 |                 new WeatherStation("Tauranga", 14.8),
440 |                 new WeatherStation("Tbilisi", 12.9),
441 |                 new WeatherStation("Tegucigalpa", 21.7),
442 |                 new WeatherStation("Tehran", 17.0),
443 |                 new WeatherStation("Tel Aviv", 20.0),
444 |                 new WeatherStation("Thessaloniki", 16.0),
445 |                 new WeatherStation("Thiès", 24.0),
446 |                 new WeatherStation("Tijuana", 17.8),
447 |                 new WeatherStation("Timbuktu", 28.0),
448 |                 new WeatherStation("Tirana", 15.2),
449 |                 new WeatherStation("Toamasina", 23.4),
450 |                 new WeatherStation("Tokyo", 15.4),
451 |                 new WeatherStation("Toliara", 24.1),
452 |                 new WeatherStation("Toluca", 12.4),
453 |                 new WeatherStation("Toronto", 9.4),
454 |                 new WeatherStation("Tripoli", 20.0),
455 |                 new WeatherStation("Tromsø", 2.9),
456 |                 new WeatherStation("Tucson", 20.9),
457 |                 new WeatherStation("Tunis", 18.4),
458 |                 new WeatherStation("Ulaanbaatar", -0.4),
459 |                 new WeatherStation("Upington", 20.4),
460 |                 new WeatherStation("Ürümqi", 7.4),
461 |                 new WeatherStation("Vaduz", 10.1),
462 |                 new WeatherStation("Valencia", 18.3),
463 |                 new WeatherStation("Valletta", 18.8),
464 |                 new WeatherStation("Vancouver", 10.4),
465 |                 new WeatherStation("Veracruz", 25.4),
466 |                 new WeatherStation("Vienna", 10.4),
467 |                 new WeatherStation("Vientiane", 25.9),
468 |                 new WeatherStation("Villahermosa", 27.1),
469 |                 new WeatherStation("Vilnius", 6.0),
470 |                 new WeatherStation("Virginia Beach", 15.8),
471 |                 new WeatherStation("Vladivostok", 4.9),
472 |                 new WeatherStation("Warsaw", 8.5),
473 |                 new WeatherStation("Washington, D.C.", 14.6),
474 |                 new WeatherStation("Wau", 27.8),
475 |                 new WeatherStation("Wellington", 12.9),
476 |                 new WeatherStation("Whitehorse", -0.1),
477 |                 new WeatherStation("Wichita", 13.9),
478 |                 new WeatherStation("Willemstad", 28.0),
479 |                 new WeatherStation("Winnipeg", 3.0),
480 |                 new WeatherStation("Wrocław", 9.6),
481 |                 new WeatherStation("Xi'an", 14.1),
482 |                 new WeatherStation("Yakutsk", -8.8),
483 |                 new WeatherStation("Yangon", 27.5),
484 |                 new WeatherStation("Yaoundé", 23.8),
485 |                 new WeatherStation("Yellowknife", -4.3),
486 |                 new WeatherStation("Yerevan", 12.4),
487 |                 new WeatherStation("Yinchuan", 9.0),
488 |                 new WeatherStation("Zagreb", 10.7),
489 |                 new WeatherStation("Zanzibar City", 26.0),
490 |                 new WeatherStation("Zürich", 9.3));
491 | 
492 |         try (BufferedWriter bw = Files.newBufferedWriter(MEASUREMENT_FILE)) {
493 |             for (int i = 0; i < size; i++) {
494 |                 if (i > 0 && i % 50_000_000 == 0) {
495 |                     System.out.printf("Wrote %,d measurements in %s ms%n", i, System.currentTimeMillis() - start);
496 |                 }
497 |                 WeatherStation station = stations.get(ThreadLocalRandom.current().nextInt(stations.size()));
498 |                 bw.write(station.id());
499 |                 bw.write(";" + station.measurement());
500 |                 bw.write('\n');
501 |             }
502 |         }
503 |         System.out.printf("Created file with %,d measurements in %s ms%n", size, System.currentTimeMillis() - start);
504 |     }
505 | }
506 | 


--------------------------------------------------------------------------------
/src/main/java/dev/morling/onebrc/CreateMeasurements2.java:
--------------------------------------------------------------------------------
  1 | /*
  2 |  *  Copyright 2023 The original authors
  3 |  *
  4 |  *  Licensed under the Apache License, Version 2.0 (the "License");
  5 |  *  you may not use this file except in compliance with the License.
  6 |  *  You may obtain a copy of the License at
  7 |  *
  8 |  *      http://www.apache.org/licenses/LICENSE-2.0
  9 |  *
 10 |  *  Unless required by applicable law or agreed to in writing, software
 11 |  *  distributed under the License is distributed on an "AS IS" BASIS,
 12 |  *  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 13 |  *  See the License for the specific language governing permissions and
 14 |  *  limitations under the License.
 15 |  */
 16 | package dev.morling.onebrc;
 17 | 
 18 | import java.io.BufferedWriter;
 19 | import java.io.File;
 20 | import java.io.FileWriter;
 21 | import java.io.IOException;
 22 | import java.util.Arrays;
 23 | import java.util.List;
 24 | import java.util.concurrent.ThreadLocalRandom;
 25 | 
 26 | import org.rschwietzke.CheaperCharBuffer;
 27 | import org.rschwietzke.FastRandom;
 28 | 
 29 | /**
 30 |  * Faster version with some data faking instead of a real Gaussian distribution
 31 |  * Good enough for our purppose I guess.
 32 |  */
 33 | public class CreateMeasurements2 {
 34 | 
 35 |     private static final String FILE = "./measurements2.txt";
 36 | 
 37 |     static class WeatherStation {
 38 |         final static char[] NUMBERS = { '0', '1', '2', '3', '4', '5', '6', '7', '8', '9' };
 39 | 
 40 |         final String id;
 41 |         final int meanTemperature;
 42 | 
 43 |         final char[] firstPart;
 44 |         final FastRandom r = new FastRandom(ThreadLocalRandom.current().nextLong());
 45 | 
 46 |         WeatherStation(String id, double meanTemperature) {
 47 |             this.id = id;
 48 |             this.meanTemperature = (int) meanTemperature;
 49 |             // make it directly copyable
 50 |             this.firstPart = (id + ";").toCharArray();
 51 |         }
 52 | 
 53 |         /**
 54 |          * We write out data into the buffer to avoid string conversion
 55 |          * We also no longer use double and gaussian, because for our
 56 |          * purpose, the fake numbers here will do it. Less
 57 |          *
 58 |          * @param buffer the buffer to append to
 59 |          */
 60 |         void measurement(final CheaperCharBuffer buffer) {
 61 |             // fake -10.9 to +10.9 variance without double operations and rounding
 62 |             // gives us -10 to +10
 63 |             int m = meanTemperature + (r.nextInt(21) - 10);
 64 |             // gives us a decimal digit 0 to 9 as char
 65 |             char d = NUMBERS[r.nextInt(10)];
 66 | 
 67 |             // just append, only one number has to be converted and we can do
 68 |             // better... if we watn
 69 |             buffer.append(firstPart, 0, firstPart.length)
 70 |                     .append(String.valueOf(m)).append('.').append(d)
 71 |                     .append('\n');
 72 |         }
 73 |     }
 74 | 
 75 |     public static void main(String[] args) throws Exception {
 76 |         long start = System.currentTimeMillis();
 77 | 
 78 |         if (args.length != 1) {
 79 |             System.out.println("Usage: create_measurements.sh <number of records to create>");
 80 |             System.exit(1);
 81 |         }
 82 | 
 83 |         int size = 0;
 84 |         try {
 85 |             size = Integer.parseInt(args[0]);
 86 |         }
 87 |         catch (NumberFormatException e) {
 88 |             System.out.println("Invalid value for <number of records to create>");
 89 |             System.out.println("Usage: CreateMeasurements <number of records to create>");
 90 |             System.exit(1);
 91 |         }
 92 | 
 93 |         // @formatter:off
 94 |         // data from https://en.wikipedia.org/wiki/List_of_cities_by_average_temperature;
 95 |         // converted using https://wikitable2csv.ggor.de/
 96 |         // brought to form using DuckDB:
 97 |         // D copy (
 98 |         //     select City, regexp_extract(Year,'(.*)\n.*', 1) as AverageTemp
 99 |         //     from (
100 |         //         select City,Year
101 |         //         from read_csv_auto('List_of_cities_by_average_temperature_1.csv', header = true)
102 |         //         union
103 |         //         select City,Year
104 |         //         from read_csv_auto('List_of_cities_by_average_temperature_2.csv', header = true)
105 |         //         union
106 |         //         select City,Year
107 |         //         from read_csv_auto('List_of_cities_by_average_temperature_3.csv', header = true)
108 |         //         union
109 |         //         select City,Year
110 |         //         from read_csv_auto('List_of_cities_by_average_temperature_4.csv', header = true)
111 |         //         union
112 |         //         select City,Year
113 |         //         from read_csv_auto('List_of_cities_by_average_temperature_5.csv', header = true)
114 |         //         )
115 |         // ) TO 'output.csv' (HEADER, DELIMITER ',');
116 |         // @formatter:on
117 |         final List<WeatherStation> stations = Arrays.asList(
118 |                 new WeatherStation("Abha", 18.0),
119 |                 new WeatherStation("Abidjan", 26.0),
120 |                 new WeatherStation("Abéché", 29.4),
121 |                 new WeatherStation("Accra", 26.4),
122 |                 new WeatherStation("Addis Ababa", 16.0),
123 |                 new WeatherStation("Adelaide", 17.3),
124 |                 new WeatherStation("Aden", 29.1),
125 |                 new WeatherStation("Ahvaz", 25.4),
126 |                 new WeatherStation("Albuquerque", 14.0),
127 |                 new WeatherStation("Alexandra", 11.0),
128 |                 new WeatherStation("Alexandria", 20.0),
129 |                 new WeatherStation("Algiers", 18.2),
130 |                 new WeatherStation("Alice Springs", 21.0),
131 |                 new WeatherStation("Almaty", 10.0),
132 |                 new WeatherStation("Amsterdam", 10.2),
133 |                 new WeatherStation("Anadyr", -6.9),
134 |                 new WeatherStation("Anchorage", 2.8),
135 |                 new WeatherStation("Andorra la Vella", 9.8),
136 |                 new WeatherStation("Ankara", 12.0),
137 |                 new WeatherStation("Antananarivo", 17.9),
138 |                 new WeatherStation("Antsiranana", 25.2),
139 |                 new WeatherStation("Arkhangelsk", 1.3),
140 |                 new WeatherStation("Ashgabat", 17.1),
141 |                 new WeatherStation("Asmara", 15.6),
142 |                 new WeatherStation("Assab", 30.5),
143 |                 new WeatherStation("Astana", 3.5),
144 |                 new WeatherStation("Athens", 19.2),
145 |                 new WeatherStation("Atlanta", 17.0),
146 |                 new WeatherStation("Auckland", 15.2),
147 |                 new WeatherStation("Austin", 20.7),
148 |                 new WeatherStation("Baghdad", 22.77),
149 |                 new WeatherStation("Baguio", 19.5),
150 |                 new WeatherStation("Baku", 15.1),
151 |                 new WeatherStation("Baltimore", 13.1),
152 |                 new WeatherStation("Bamako", 27.8),
153 |                 new WeatherStation("Bangkok", 28.6),
154 |                 new WeatherStation("Bangui", 26.0),
155 |                 new WeatherStation("Banjul", 26.0),
156 |                 new WeatherStation("Barcelona", 18.2),
157 |                 new WeatherStation("Bata", 25.1),
158 |                 new WeatherStation("Batumi", 14.0),
159 |                 new WeatherStation("Beijing", 12.9),
160 |                 new WeatherStation("Beirut", 20.9),
161 |                 new WeatherStation("Belgrade", 12.5),
162 |                 new WeatherStation("Belize City", 26.7),
163 |                 new WeatherStation("Benghazi", 19.9),
164 |                 new WeatherStation("Bergen", 7.7),
165 |                 new WeatherStation("Berlin", 10.3),
166 |                 new WeatherStation("Bilbao", 14.7),
167 |                 new WeatherStation("Birao", 26.5),
168 |                 new WeatherStation("Bishkek", 11.3),
169 |                 new WeatherStation("Bissau", 27.0),
170 |                 new WeatherStation("Blantyre", 22.2),
171 |                 new WeatherStation("Bloemfontein", 15.6),
172 |                 new WeatherStation("Boise", 11.4),
173 |                 new WeatherStation("Bordeaux", 14.2),
174 |                 new WeatherStation("Bosaso", 30.0),
175 |                 new WeatherStation("Boston", 10.9),
176 |                 new WeatherStation("Bouaké", 26.0),
177 |                 new WeatherStation("Bratislava", 10.5),
178 |                 new WeatherStation("Brazzaville", 25.0),
179 |                 new WeatherStation("Bridgetown", 27.0),
180 |                 new WeatherStation("Brisbane", 21.4),
181 |                 new WeatherStation("Brussels", 10.5),
182 |                 new WeatherStation("Bucharest", 10.8),
183 |                 new WeatherStation("Budapest", 11.3),
184 |                 new WeatherStation("Bujumbura", 23.8),
185 |                 new WeatherStation("Bulawayo", 18.9),
186 |                 new WeatherStation("Burnie", 13.1),
187 |                 new WeatherStation("Busan", 15.0),
188 |                 new WeatherStation("Cabo San Lucas", 23.9),
189 |                 new WeatherStation("Cairns", 25.0),
190 |                 new WeatherStation("Cairo", 21.4),
191 |                 new WeatherStation("Calgary", 4.4),
192 |                 new WeatherStation("Canberra", 13.1),
193 |                 new WeatherStation("Cape Town", 16.2),
194 |                 new WeatherStation("Changsha", 17.4),
195 |                 new WeatherStation("Charlotte", 16.1),
196 |                 new WeatherStation("Chiang Mai", 25.8),
197 |                 new WeatherStation("Chicago", 9.8),
198 |                 new WeatherStation("Chihuahua", 18.6),
199 |                 new WeatherStation("Chișinău", 10.2),
200 |                 new WeatherStation("Chittagong", 25.9),
201 |                 new WeatherStation("Chongqing", 18.6),
202 |                 new WeatherStation("Christchurch", 12.2),
203 |                 new WeatherStation("City of San Marino", 11.8),
204 |                 new WeatherStation("Colombo", 27.4),
205 |                 new WeatherStation("Columbus", 11.7),
206 |                 new WeatherStation("Conakry", 26.4),
207 |                 new WeatherStation("Copenhagen", 9.1),
208 |                 new WeatherStation("Cotonou", 27.2),
209 |                 new WeatherStation("Cracow", 9.3),
210 |                 new WeatherStation("Da Lat", 17.9),
211 |                 new WeatherStation("Da Nang", 25.8),
212 |                 new WeatherStation("Dakar", 24.0),
213 |                 new WeatherStation("Dallas", 19.0),
214 |                 new WeatherStation("Damascus", 17.0),
215 |                 new WeatherStation("Dampier", 26.4),
216 |                 new WeatherStation("Dar es Salaam", 25.8),
217 |                 new WeatherStation("Darwin", 27.6),
218 |                 new WeatherStation("Denpasar", 23.7),
219 |                 new WeatherStation("Denver", 10.4),
220 |                 new WeatherStation("Detroit", 10.0),
221 |                 new WeatherStation("Dhaka", 25.9),
222 |                 new WeatherStation("Dikson", -11.1),
223 |                 new WeatherStation("Dili", 26.6),
224 |                 new WeatherStation("Djibouti", 29.9),
225 |                 new WeatherStation("Dodoma", 22.7),
226 |                 new WeatherStation("Dolisie", 24.0),
227 |                 new WeatherStation("Douala", 26.7),
228 |                 new WeatherStation("Dubai", 26.9),
229 |                 new WeatherStation("Dublin", 9.8),
230 |                 new WeatherStation("Dunedin", 11.1),
231 |                 new WeatherStation("Durban", 20.6),
232 |                 new WeatherStation("Dushanbe", 14.7),
233 |                 new WeatherStation("Edinburgh", 9.3),
234 |                 new WeatherStation("Edmonton", 4.2),
235 |                 new WeatherStation("El Paso", 18.1),
236 |                 new WeatherStation("Entebbe", 21.0),
237 |                 new WeatherStation("Erbil", 19.5),
238 |                 new WeatherStation("Erzurum", 5.1),
239 |                 new WeatherStation("Fairbanks", -2.3),
240 |                 new WeatherStation("Fianarantsoa", 17.9),
241 |                 new WeatherStation("Flores,  Petén", 26.4),
242 |                 new WeatherStation("Frankfurt", 10.6),
243 |                 new WeatherStation("Fresno", 17.9),
244 |                 new WeatherStation("Fukuoka", 17.0),
245 |                 new WeatherStation("Gabès", 19.5),
246 |                 new WeatherStation("Gaborone", 21.0),
247 |                 new WeatherStation("Gagnoa", 26.0),
248 |                 new WeatherStation("Gangtok", 15.2),
249 |                 new WeatherStation("Garissa", 29.3),
250 |                 new WeatherStation("Garoua", 28.3),
251 |                 new WeatherStation("George Town", 27.9),
252 |                 new WeatherStation("Ghanzi", 21.4),
253 |                 new WeatherStation("Gjoa Haven", -14.4),
254 |                 new WeatherStation("Guadalajara", 20.9),
255 |                 new WeatherStation("Guangzhou", 22.4),
256 |                 new WeatherStation("Guatemala City", 20.4),
257 |                 new WeatherStation("Halifax", 7.5),
258 |                 new WeatherStation("Hamburg", 9.7),
259 |                 new WeatherStation("Hamilton", 13.8),
260 |                 new WeatherStation("Hanga Roa", 20.5),
261 |                 new WeatherStation("Hanoi", 23.6),
262 |                 new WeatherStation("Harare", 18.4),
263 |                 new WeatherStation("Harbin", 5.0),
264 |                 new WeatherStation("Hargeisa", 21.7),
265 |                 new WeatherStation("Hat Yai", 27.0),
266 |                 new WeatherStation("Havana", 25.2),
267 |                 new WeatherStation("Helsinki", 5.9),
268 |                 new WeatherStation("Heraklion", 18.9),
269 |                 new WeatherStation("Hiroshima", 16.3),
270 |                 new WeatherStation("Ho Chi Minh City", 27.4),
271 |                 new WeatherStation("Hobart", 12.7),
272 |                 new WeatherStation("Hong Kong", 23.3),
273 |                 new WeatherStation("Honiara", 26.5),
274 |                 new WeatherStation("Honolulu", 25.4),
275 |                 new WeatherStation("Houston", 20.8),
276 |                 new WeatherStation("Ifrane", 11.4),
277 |                 new WeatherStation("Indianapolis", 11.8),
278 |                 new WeatherStation("Iqaluit", -9.3),
279 |                 new WeatherStation("Irkutsk", 1.0),
280 |                 new WeatherStation("Istanbul", 13.9),
281 |                 new WeatherStation("İzmir", 17.9),
282 |                 new WeatherStation("Jacksonville", 20.3),
283 |                 new WeatherStation("Jakarta", 26.7),
284 |                 new WeatherStation("Jayapura", 27.0),
285 |                 new WeatherStation("Jerusalem", 18.3),
286 |                 new WeatherStation("Johannesburg", 15.5),
287 |                 new WeatherStation("Jos", 22.8),
288 |                 new WeatherStation("Juba", 27.8),
289 |                 new WeatherStation("Kabul", 12.1),
290 |                 new WeatherStation("Kampala", 20.0),
291 |                 new WeatherStation("Kandi", 27.7),
292 |                 new WeatherStation("Kankan", 26.5),
293 |                 new WeatherStation("Kano", 26.4),
294 |                 new WeatherStation("Kansas City", 12.5),
295 |                 new WeatherStation("Karachi", 26.0),
296 |                 new WeatherStation("Karonga", 24.4),
297 |                 new WeatherStation("Kathmandu", 18.3),
298 |                 new WeatherStation("Khartoum", 29.9),
299 |                 new WeatherStation("Kingston", 27.4),
300 |                 new WeatherStation("Kinshasa", 25.3),
301 |                 new WeatherStation("Kolkata", 26.7),
302 |                 new WeatherStation("Kuala Lumpur", 27.3),
303 |                 new WeatherStation("Kumasi", 26.0),
304 |                 new WeatherStation("Kunming", 15.7),
305 |                 new WeatherStation("Kuopio", 3.4),
306 |                 new WeatherStation("Kuwait City", 25.7),
307 |                 new WeatherStation("Kyiv", 8.4),
308 |                 new WeatherStation("Kyoto", 15.8),
309 |                 new WeatherStation("La Ceiba", 26.2),
310 |                 new WeatherStation("La Paz", 23.7),
311 |                 new WeatherStation("Lagos", 26.8),
312 |                 new WeatherStation("Lahore", 24.3),
313 |                 new WeatherStation("Lake Havasu City", 23.7),
314 |                 new WeatherStation("Lake Tekapo", 8.7),
315 |                 new WeatherStation("Las Palmas de Gran Canaria", 21.2),
316 |                 new WeatherStation("Las Vegas", 20.3),
317 |                 new WeatherStation("Launceston", 13.1),
318 |                 new WeatherStation("Lhasa", 7.6),
319 |                 new WeatherStation("Libreville", 25.9),
320 |                 new WeatherStation("Lisbon", 17.5),
321 |                 new WeatherStation("Livingstone", 21.8),
322 |                 new WeatherStation("Ljubljana", 10.9),
323 |                 new WeatherStation("Lodwar", 29.3),
324 |                 new WeatherStation("Lomé", 26.9),
325 |                 new WeatherStation("London", 11.3),
326 |                 new WeatherStation("Los Angeles", 18.6),
327 |                 new WeatherStation("Louisville", 13.9),
328 |                 new WeatherStation("Luanda", 25.8),
329 |                 new WeatherStation("Lubumbashi", 20.8),
330 |                 new WeatherStation("Lusaka", 19.9),
331 |                 new WeatherStation("Luxembourg City", 9.3),
332 |                 new WeatherStation("Lviv", 7.8),
333 |                 new WeatherStation("Lyon", 12.5),
334 |                 new WeatherStation("Madrid", 15.0),
335 |                 new WeatherStation("Mahajanga", 26.3),
336 |                 new WeatherStation("Makassar", 26.7),
337 |                 new WeatherStation("Makurdi", 26.0),
338 |                 new WeatherStation("Malabo", 26.3),
339 |                 new WeatherStation("Malé", 28.0),
340 |                 new WeatherStation("Managua", 27.3),
341 |                 new WeatherStation("Manama", 26.5),
342 |                 new WeatherStation("Mandalay", 28.0),
343 |                 new WeatherStation("Mango", 28.1),
344 |                 new WeatherStation("Manila", 28.4),
345 |                 new WeatherStation("Maputo", 22.8),
346 |                 new WeatherStation("Marrakesh", 19.6),
347 |                 new WeatherStation("Marseille", 15.8),
348 |                 new WeatherStation("Maun", 22.4),
349 |                 new WeatherStation("Medan", 26.5),
350 |                 new WeatherStation("Mek'ele", 22.7),
351 |                 new WeatherStation("Melbourne", 15.1),
352 |                 new WeatherStation("Memphis", 17.2),
353 |                 new WeatherStation("Mexicali", 23.1),
354 |                 new WeatherStation("Mexico City", 17.5),
355 |                 new WeatherStation("Miami", 24.9),
356 |                 new WeatherStation("Milan", 13.0),
357 |                 new WeatherStation("Milwaukee", 8.9),
358 |                 new WeatherStation("Minneapolis", 7.8),
359 |                 new WeatherStation("Minsk", 6.7),
360 |                 new WeatherStation("Mogadishu", 27.1),
361 |                 new WeatherStation("Mombasa", 26.3),
362 |                 new WeatherStation("Monaco", 16.4),
363 |                 new WeatherStation("Moncton", 6.1),
364 |                 new WeatherStation("Monterrey", 22.3),
365 |                 new WeatherStation("Montreal", 6.8),
366 |                 new WeatherStation("Moscow", 5.8),
367 |                 new WeatherStation("Mumbai", 27.1),
368 |                 new WeatherStation("Murmansk", 0.6),
369 |                 new WeatherStation("Muscat", 28.0),
370 |                 new WeatherStation("Mzuzu", 17.7),
371 |                 new WeatherStation("N'Djamena", 28.3),
372 |                 new WeatherStation("Naha", 23.1),
373 |                 new WeatherStation("Nairobi", 17.8),
374 |                 new WeatherStation("Nakhon Ratchasima", 27.3),
375 |                 new WeatherStation("Napier", 14.6),
376 |                 new WeatherStation("Napoli", 15.9),
377 |                 new WeatherStation("Nashville", 15.4),
378 |                 new WeatherStation("Nassau", 24.6),
379 |                 new WeatherStation("Ndola", 20.3),
380 |                 new WeatherStation("New Delhi", 25.0),
381 |                 new WeatherStation("New Orleans", 20.7),
382 |                 new WeatherStation("New York City", 12.9),
383 |                 new WeatherStation("Ngaoundéré", 22.0),
384 |                 new WeatherStation("Niamey", 29.3),
385 |                 new WeatherStation("Nicosia", 19.7),
386 |                 new WeatherStation("Niigata", 13.9),
387 |                 new WeatherStation("Nouadhibou", 21.3),
388 |                 new WeatherStation("Nouakchott", 25.7),
389 |                 new WeatherStation("Novosibirsk", 1.7),
390 |                 new WeatherStation("Nuuk", -1.4),
391 |                 new WeatherStation("Odesa", 10.7),
392 |                 new WeatherStation("Odienné", 26.0),
393 |                 new WeatherStation("Oklahoma City", 15.9),
394 |                 new WeatherStation("Omaha", 10.6),
395 |                 new WeatherStation("Oranjestad", 28.1),
396 |                 new WeatherStation("Oslo", 5.7),
397 |                 new WeatherStation("Ottawa", 6.6),
398 |                 new WeatherStation("Ouagadougou", 28.3),
399 |                 new WeatherStation("Ouahigouya", 28.6),
400 |                 new WeatherStation("Ouarzazate", 18.9),
401 |                 new WeatherStation("Oulu", 2.7),
402 |                 new WeatherStation("Palembang", 27.3),
403 |                 new WeatherStation("Palermo", 18.5),
404 |                 new WeatherStation("Palm Springs", 24.5),
405 |                 new WeatherStation("Palmerston North", 13.2),
406 |                 new WeatherStation("Panama City", 28.0),
407 |                 new WeatherStation("Parakou", 26.8),
408 |                 new WeatherStation("Paris", 12.3),
409 |                 new WeatherStation("Perth", 18.7),
410 |                 new WeatherStation("Petropavlovsk-Kamchatsky", 1.9),
411 |                 new WeatherStation("Philadelphia", 13.2),
412 |                 new WeatherStation("Phnom Penh", 28.3),
413 |                 new WeatherStation("Phoenix", 23.9),
414 |                 new WeatherStation("Pittsburgh", 10.8),
415 |                 new WeatherStation("Podgorica", 15.3),
416 |                 new WeatherStation("Pointe-Noire", 26.1),
417 |                 new WeatherStation("Pontianak", 27.7),
418 |                 new WeatherStation("Port Moresby", 26.9),
419 |                 new WeatherStation("Port Sudan", 28.4),
420 |                 new WeatherStation("Port Vila", 24.3),
421 |                 new WeatherStation("Port-Gentil", 26.0),
422 |                 new WeatherStation("Portland (OR)", 12.4),
423 |                 new WeatherStation("Porto", 15.7),
424 |                 new WeatherStation("Prague", 8.4),
425 |                 new WeatherStation("Praia", 24.4),
426 |                 new WeatherStation("Pretoria", 18.2),
427 |                 new WeatherStation("Pyongyang", 10.8),
428 |                 new WeatherStation("Rabat", 17.2),
429 |                 new WeatherStation("Rangpur", 24.4),
430 |                 new WeatherStation("Reggane", 28.3),
431 |                 new WeatherStation("Reykjavík", 4.3),
432 |                 new WeatherStation("Riga", 6.2),
433 |                 new WeatherStation("Riyadh", 26.0),
434 |                 new WeatherStation("Rome", 15.2),
435 |                 new WeatherStation("Roseau", 26.2),
436 |                 new WeatherStation("Rostov-on-Don", 9.9),
437 |                 new WeatherStation("Sacramento", 16.3),
438 |                 new WeatherStation("Saint Petersburg", 5.8),
439 |                 new WeatherStation("Saint-Pierre", 5.7),
440 |                 new WeatherStation("Salt Lake City", 11.6),
441 |                 new WeatherStation("San Antonio", 20.8),
442 |                 new WeatherStation("San Diego", 17.8),
443 |                 new WeatherStation("San Francisco", 14.6),
444 |                 new WeatherStation("San Jose", 16.4),
445 |                 new WeatherStation("San José", 22.6),
446 |                 new WeatherStation("San Juan", 27.2),
447 |                 new WeatherStation("San Salvador", 23.1),
448 |                 new WeatherStation("Sana'a", 20.0),
449 |                 new WeatherStation("Santo Domingo", 25.9),
450 |                 new WeatherStation("Sapporo", 8.9),
451 |                 new WeatherStation("Sarajevo", 10.1),
452 |                 new WeatherStation("Saskatoon", 3.3),
453 |                 new WeatherStation("Seattle", 11.3),
454 |                 new WeatherStation("Ségou", 28.0),
455 |                 new WeatherStation("Seoul", 12.5),
456 |                 new WeatherStation("Seville", 19.2),
457 |                 new WeatherStation("Shanghai", 16.7),
458 |                 new WeatherStation("Singapore", 27.0),
459 |                 new WeatherStation("Skopje", 12.4),
460 |                 new WeatherStation("Sochi", 14.2),
461 |                 new WeatherStation("Sofia", 10.6),
462 |                 new WeatherStation("Sokoto", 28.0),
463 |                 new WeatherStation("Split", 16.1),
464 |                 new WeatherStation("St. John's", 5.0),
465 |                 new WeatherStation("St. Louis", 13.9),
466 |                 new WeatherStation("Stockholm", 6.6),
467 |                 new WeatherStation("Surabaya", 27.1),
468 |                 new WeatherStation("Suva", 25.6),
469 |                 new WeatherStation("Suwałki", 7.2),
470 |                 new WeatherStation("Sydney", 17.7),
471 |                 new WeatherStation("Tabora", 23.0),
472 |                 new WeatherStation("Tabriz", 12.6),
473 |                 new WeatherStation("Taipei", 23.0),
474 |                 new WeatherStation("Tallinn", 6.4),
475 |                 new WeatherStation("Tamale", 27.9),
476 |                 new WeatherStation("Tamanrasset", 21.7),
477 |                 new WeatherStation("Tampa", 22.9),
478 |                 new WeatherStation("Tashkent", 14.8),
479 |                 new WeatherStation("Tauranga", 14.8),
480 |                 new WeatherStation("Tbilisi", 12.9),
481 |                 new WeatherStation("Tegucigalpa", 21.7),
482 |                 new WeatherStation("Tehran", 17.0),
483 |                 new WeatherStation("Tel Aviv", 20.0),
484 |                 new WeatherStation("Thessaloniki", 16.0),
485 |                 new WeatherStation("Thiès", 24.0),
486 |                 new WeatherStation("Tijuana", 17.8),
487 |                 new WeatherStation("Timbuktu", 28.0),
488 |                 new WeatherStation("Tirana", 15.2),
489 |                 new WeatherStation("Toamasina", 23.4),
490 |                 new WeatherStation("Tokyo", 15.4),
491 |                 new WeatherStation("Toliara", 24.1),
492 |                 new WeatherStation("Toluca", 12.4),
493 |                 new WeatherStation("Toronto", 9.4),
494 |                 new WeatherStation("Tripoli", 20.0),
495 |                 new WeatherStation("Tromsø", 2.9),
496 |                 new WeatherStation("Tucson", 20.9),
497 |                 new WeatherStation("Tunis", 18.4),
498 |                 new WeatherStation("Ulaanbaatar", -0.4),
499 |                 new WeatherStation("Upington", 20.4),
500 |                 new WeatherStation("Ürümqi", 7.4),
501 |                 new WeatherStation("Vaduz", 10.1),
502 |                 new WeatherStation("Valencia", 18.3),
503 |                 new WeatherStation("Valletta", 18.8),
504 |                 new WeatherStation("Vancouver", 10.4),
505 |                 new WeatherStation("Veracruz", 25.4),
506 |                 new WeatherStation("Vienna", 10.4),
507 |                 new WeatherStation("Vientiane", 25.9),
508 |                 new WeatherStation("Villahermosa", 27.1),
509 |                 new WeatherStation("Vilnius", 6.0),
510 |                 new WeatherStation("Virginia Beach", 15.8),
511 |                 new WeatherStation("Vladivostok", 4.9),
512 |                 new WeatherStation("Warsaw", 8.5),
513 |                 new WeatherStation("Washington, D.C.", 14.6),
514 |                 new WeatherStation("Wau", 27.8),
515 |                 new WeatherStation("Wellington", 12.9),
516 |                 new WeatherStation("Whitehorse", -0.1),
517 |                 new WeatherStation("Wichita", 13.9),
518 |                 new WeatherStation("Willemstad", 28.0),
519 |                 new WeatherStation("Winnipeg", 3.0),
520 |                 new WeatherStation("Wrocław", 9.6),
521 |                 new WeatherStation("Xi'an", 14.1),
522 |                 new WeatherStation("Yakutsk", -8.8),
523 |                 new WeatherStation("Yangon", 27.5),
524 |                 new WeatherStation("Yaoundé", 23.8),
525 |                 new WeatherStation("Yellowknife", -4.3),
526 |                 new WeatherStation("Yerevan", 12.4),
527 |                 new WeatherStation("Yinchuan", 9.0),
528 |                 new WeatherStation("Zagreb", 10.7),
529 |                 new WeatherStation("Zanzibar City", 26.0),
530 |                 new WeatherStation("Zürich", 9.3));
531 | 
532 |         File file = new File(FILE);
533 | 
534 |         // break the loop and unroll it manually
535 |         int strideSize = 50_000_000;
536 |         int outer = size / strideSize;
537 |         int remainder = size - (outer * strideSize);
538 | 
539 |         try (final BufferedWriter bw = new BufferedWriter(new FileWriter(file))) {
540 |             for (int i = 0; i < outer; i++) {
541 |                 produce(bw, stations, strideSize);
542 | 
543 |                 // we avoid a modulo if here and use the stride size to print and update
544 |                 System.out.println("Wrote %,d measurements in %s ms".formatted((i + 1) * strideSize, System.currentTimeMillis() - start));
545 |             }
546 |             // there might be a rest
547 |             produce(bw, stations, remainder);
548 | 
549 |             // write fully before taking measurements
550 |             bw.flush();
551 |             System.out.println("Created file with %,d measurements in %s ms".formatted(size, System.currentTimeMillis() - start));
552 |         }
553 |     }
554 | 
555 |     private static void produce(BufferedWriter bw, List<WeatherStation> stations, int count) throws IOException {
556 |         final int stationCount = stations.size();
557 |         final int rest = count % 8;
558 | 
559 |         // use a fast ranodm impl without atomics to be able to utilize the cpu better
560 |         // and avoid sideeffects, FastRandom is very fake random and does not have a state
561 |         final FastRandom r1 = new FastRandom(ThreadLocalRandom.current().nextLong());
562 |         final FastRandom r2 = new FastRandom(ThreadLocalRandom.current().nextLong());
563 |         final FastRandom r3 = new FastRandom(ThreadLocalRandom.current().nextLong());
564 |         final FastRandom r4 = new FastRandom(ThreadLocalRandom.current().nextLong());
565 | 
566 |         // write to a fix buffer first, don't create strings ever
567 |         // reuse buffer
568 |         final CheaperCharBuffer sb = new CheaperCharBuffer(200);
569 | 
570 |         // manual loop unroll for less jumps
571 |         for (int i = 0; i < count; i = i + 8) {
572 |             {
573 |                 // try to fill teh cpu pipeline as much as possible with
574 |                 // independent operations
575 |                 int s1 = r1.nextInt(stationCount);
576 |                 int s2 = r2.nextInt(stationCount);
577 |                 int s3 = r3.nextInt(stationCount);
578 |                 int s4 = r4.nextInt(stationCount);
579 |                 // get us the ojects one after the other to have the array
580 |                 // in our L1 cache and not push it out with other data
581 |                 var w1 = stations.get(s1);
582 |                 var w2 = stations.get(s2);
583 |                 var w3 = stations.get(s3);
584 |                 var w4 = stations.get(s4);
585 |                 // write our data to our buffer
586 |                 w1.measurement(sb);
587 |                 w2.measurement(sb);
588 |                 w3.measurement(sb);
589 |                 w4.measurement(sb);
590 |             }
591 |             {
592 |                 int s1 = r1.nextInt(stationCount);
593 |                 int s2 = r2.nextInt(stationCount);
594 |                 int s3 = r3.nextInt(stationCount);
595 |                 int s4 = r4.nextInt(stationCount);
596 |                 var w1 = stations.get(s1);
597 |                 var w2 = stations.get(s2);
598 |                 var w3 = stations.get(s3);
599 |                 var w4 = stations.get(s4);
600 |                 w1.measurement(sb);
601 |                 w2.measurement(sb);
602 |                 w3.measurement(sb);
603 |                 w4.measurement(sb);
604 |             }
605 |             // write the buffer directly, no intermediate string copy
606 |             bw.write(sb.data_, 0, sb.length_);
607 | 
608 |             // reuse buffer, reset only, no cleaning
609 |             sb.clear();
610 |         }
611 | 
612 |         // there might be a rest to write
613 |         for (int i = 0; i < rest; i++) {
614 |             sb.clear();
615 | 
616 |             int s = r1.nextInt(stationCount);
617 |             var w = stations.get(s);
618 |             w.measurement(sb);
619 | 
620 |             bw.write(sb.data_, 0, sb.length_);
621 |         }
622 |     }
623 | }
624 | 


--------------------------------------------------------------------------------
/src/main/java/dev/morling/onebrc/CreateMeasurements3.java:
--------------------------------------------------------------------------------
  1 | /*
  2 |  *  Copyright 2023 The original authors
  3 |  *
  4 |  *  Licensed under the Apache License, Version 2.0 (the "License");
  5 |  *  you may not use this file except in compliance with the License.
  6 |  *  You may obtain a copy of the License at
  7 |  *
  8 |  *      http://www.apache.org/licenses/LICENSE-2.0
  9 |  *
 10 |  *  Unless required by applicable law or agreed to in writing, software
 11 |  *  distributed under the License is distributed on an "AS IS" BASIS,
 12 |  *  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 13 |  *  See the License for the specific language governing permissions and
 14 |  *  limitations under the License.
 15 |  */
 16 | package dev.morling.onebrc;
 17 | 
 18 | import java.io.BufferedReader;
 19 | import java.io.BufferedWriter;
 20 | import java.io.FileReader;
 21 | import java.io.FileWriter;
 22 | import java.io.IOException;
 23 | import java.io.StringReader;
 24 | import java.nio.charset.StandardCharsets;
 25 | import java.util.ArrayList;
 26 | import java.util.HashSet;
 27 | import java.util.concurrent.ThreadLocalRandom;
 28 | 
 29 | public class CreateMeasurements3 {
 30 | 
 31 |     public static final int MAX_NAME_LEN = 100;
 32 |     public static final int KEYSET_SIZE = 10_000;
 33 | 
 34 |     public static void main(String[] args) throws Exception {
 35 |         if (args.length != 1) {
 36 |             System.out.println("Usage: create_measurements3.sh <number of records to create>");
 37 |             System.exit(1);
 38 |         }
 39 |         int size = 0;
 40 |         try {
 41 |             size = Integer.parseInt(args[0]);
 42 |         }
 43 |         catch (NumberFormatException e) {
 44 |             System.out.println("Invalid value for <number of records to create>");
 45 |             System.out.println("Usage: create_measurements3.sh <number of records to create>");
 46 |             System.exit(1);
 47 |         }
 48 |         final var weatherStations = generateWeatherStations();
 49 |         final var start = System.currentTimeMillis();
 50 |         final var rnd = ThreadLocalRandom.current();
 51 |         try (var out = new BufferedWriter(new FileWriter("measurements.txt"))) {
 52 |             for (int i = 1; i <= size; i++) {
 53 |                 var station = weatherStations.get(rnd.nextInt(KEYSET_SIZE));
 54 |                 double temp = rnd.nextGaussian(station.avgTemp, 7.0);
 55 |                 out.write(station.name);
 56 |                 out.write(';');
 57 |                 out.write(Double.toString(Math.round(temp * 10.0) / 10.0));
 58 |                 out.newLine();
 59 |                 if (i % 50_000_000 == 0) {
 60 |                     System.out.printf("Wrote %,d measurements in %,d ms%n", i, System.currentTimeMillis() - start);
 61 |                 }
 62 |             }
 63 |         }
 64 |     }
 65 | 
 66 |     record WeatherStation(String name, float avgTemp) {
 67 |     }
 68 | 
 69 |     private static ArrayList<WeatherStation> generateWeatherStations() throws Exception {
 70 |         // Use a public list of city names and concatenate them all into a long string,
 71 |         // which we'll use as a "source of city name randomness"
 72 |         var bigName = new StringBuilder(1 << 20);
 73 |         try (var rows = new BufferedReader(new FileReader("data/weather_stations.csv"));) {
 74 |             skipComments(rows);
 75 |             while (true) {
 76 |                 var row = rows.readLine();
 77 |                 if (row == null) {
 78 |                     break;
 79 |                 }
 80 |                 bigName.append(row, 0, row.indexOf(';'));
 81 |             }
 82 |         }
 83 |         final var weatherStations = new ArrayList<WeatherStation>();
 84 |         final var names = new HashSet<String>();
 85 |         var minLen = Integer.MAX_VALUE;
 86 |         var maxLen = Integer.MIN_VALUE;
 87 |         try (var rows = new BufferedReader(new FileReader("data/weather_stations.csv"))) {
 88 |             skipComments(rows);
 89 |             final var nameSource = new StringReader(bigName.toString());
 90 |             final var buf = new char[MAX_NAME_LEN];
 91 |             final var rnd = ThreadLocalRandom.current();
 92 |             final double yOffset = 4;
 93 |             final double factor = 2500;
 94 |             final double xOffset = 0.372;
 95 |             final double power = 7;
 96 |             for (int i = 0; i < KEYSET_SIZE; i++) {
 97 |                 var row = rows.readLine();
 98 |                 if (row == null) {
 99 |                     break;
100 |                 }
101 |                 // Use a 7th-order curve to simulate the name length distribution.
102 |                 // It gives us mostly short names, but with large outliers.
103 |                 var nameLen = (int) (yOffset + factor * Math.pow(rnd.nextDouble() - xOffset, power));
104 |                 var count = nameSource.read(buf, 0, nameLen);
105 |                 if (count == -1) {
106 |                     throw new Exception("Name source exhausted");
107 |                 }
108 |                 var nameBuf = new StringBuilder(nameLen);
109 |                 nameBuf.append(buf, 0, nameLen);
110 |                 if (Character.isWhitespace(nameBuf.charAt(0))) {
111 |                     nameBuf.setCharAt(0, readNonSpace(nameSource));
112 |                 }
113 |                 if (Character.isWhitespace(nameBuf.charAt(nameBuf.length() - 1))) {
114 |                     nameBuf.setCharAt(nameBuf.length() - 1, readNonSpace(nameSource));
115 |                 }
116 |                 var name = nameBuf.toString();
117 |                 while (names.contains(name)) {
118 |                     nameBuf.setCharAt(rnd.nextInt(nameBuf.length()), readNonSpace(nameSource));
119 |                     name = nameBuf.toString();
120 |                 }
121 |                 int actualLen;
122 |                 while (true) {
123 |                     actualLen = name.getBytes(StandardCharsets.UTF_8).length;
124 |                     if (actualLen <= 100) {
125 |                         break;
126 |                     }
127 |                     nameBuf.deleteCharAt(nameBuf.length() - 1);
128 |                     if (Character.isWhitespace(nameBuf.charAt(nameBuf.length() - 1))) {
129 |                         nameBuf.setCharAt(nameBuf.length() - 1, readNonSpace(nameSource));
130 |                     }
131 |                     name = nameBuf.toString();
132 |                 }
133 |                 if (name.indexOf(';') != -1) {
134 |                     throw new Exception("Station name contains a semicolon!");
135 |                 }
136 |                 names.add(name);
137 |                 minLen = Integer.min(minLen, actualLen);
138 |                 maxLen = Integer.max(maxLen, actualLen);
139 |                 var lat = Float.parseFloat(row.substring(row.indexOf(';') + 1));
140 |                 // Guesstimate mean temperature using cosine of latitude
141 |                 var avgTemp = (float) (30 * Math.cos(Math.toRadians(lat))) - 10;
142 |                 weatherStations.add(new WeatherStation(name, avgTemp));
143 |             }
144 |         }
145 |         System.out.format("Generated %,d station names with length from %,d to %,d%n", KEYSET_SIZE, minLen, maxLen);
146 |         return weatherStations;
147 |     }
148 | 
149 |     private static void skipComments(BufferedReader rows) throws IOException {
150 |         while (rows.readLine().startsWith("#")) {
151 |         }
152 |     }
153 | 
154 |     private static char readNonSpace(StringReader nameSource) throws IOException {
155 |         while (true) {
156 |             var n = nameSource.read();
157 |             if (n == -1) {
158 |                 throw new IOException("Name source exhausted");
159 |             }
160 |             var ch = (char) n;
161 |             if (ch != ' ') {
162 |                 return ch;
163 |             }
164 |         }
165 |     }
166 | }
167 | 


--------------------------------------------------------------------------------
/src/main/java/org/rschwietzke/CheaperCharBuffer.java:
--------------------------------------------------------------------------------
  1 | /*
  2 |  *  Copyright 2023 The original authors
  3 |  *
  4 |  *  Licensed under the Apache License, Version 2.0 (the "License");
  5 |  *  you may not use this file except in compliance with the License.
  6 |  *  You may obtain a copy of the License at
  7 |  *
  8 |  *      http://www.apache.org/licenses/LICENSE-2.0
  9 |  *
 10 |  *  Unless required by applicable law or agreed to in writing, software
 11 |  *  distributed under the License is distributed on an "AS IS" BASIS,
 12 |  *  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 13 |  *  See the License for the specific language governing permissions and
 14 |  *  limitations under the License.
 15 |  */
 16 | package org.rschwietzke;
 17 | 
 18 | import java.util.Arrays;
 19 | 
 20 | /**
 21 |  * <p>This class is meant to replaces the old {@link CheaperCharBuffer} in all areas
 22 |  * where performance and memory-efficency is key. XMLString compatibility
 23 |  * remains in place in case one has used that in their own code.
 24 |  *
 25 |  * <p>This buffer is mutable and when you use it, make sure you work with
 26 |  * it responsibly. In many cases, we will reuse the buffer to avoid fresh
 27 |  * memory allocations, hence you have to pay attention to its usage pattern.
 28 |  * It is not meant to be a general String replacement.
 29 |  *
 30 |  * <p>This class avoids many of the standard runtime checks that will result
 31 |  * in a runtime or array exception anyway. Why check twice and raise the
 32 |  * same exception?
 33 |  *
 34 |  * @author René Schwietzke
 35 |  * @since 3.10.0
 36 |  */
 37 | public class CheaperCharBuffer implements CharSequence {
 38 |     // our data, can grow - that is not safe and has be altered from the original code
 39 |     // to allow speed
 40 |     public char[] data_;
 41 | 
 42 |     // the current size of the string data
 43 |     public int length_;
 44 | 
 45 |     // the current size of the string data
 46 |     private final int growBy_;
 47 | 
 48 |     // how much do we grow if needed, half a cache line
 49 |     public static final int CAPACITY_GROWTH = 64 / 2;
 50 | 
 51 |     // what is our start size?
 52 |     // a cache line is 64 byte mostly, the overhead is mostly 24 bytes
 53 |     // a char is two bytes, let's use one cache lines
 54 |     public static final int INITIAL_CAPACITY = (64 - 24) / 2;
 55 | 
 56 |     // static empty version; DON'T MODIFY IT
 57 |     public static final CheaperCharBuffer EMPTY = new CheaperCharBuffer(0);
 58 | 
 59 |     // the � character
 60 |     private static final char REPLACEMENT_CHARACTER = '\uFFFD';
 61 | 
 62 |     /**
 63 |      * Constructs an XMLCharBuffer with a default size.
 64 |      */
 65 |     public CheaperCharBuffer() {
 66 |         this.data_ = new char[INITIAL_CAPACITY];
 67 |         this.length_ = 0;
 68 |         this.growBy_ = CAPACITY_GROWTH;
 69 |     }
 70 | 
 71 |     /**
 72 |      * Constructs an XMLCharBuffer with a desired size.
 73 |      *
 74 |      * @param startSize the size of the buffer to start with
 75 |      */
 76 |     public CheaperCharBuffer(final int startSize) {
 77 |         this(startSize, CAPACITY_GROWTH);
 78 |     }
 79 | 
 80 |     /**
 81 |      * Constructs an XMLCharBuffer with a desired size.
 82 |      *
 83 |      * @param startSize the size of the buffer to start with
 84 |      * @param growBy by how much do we want to grow when needed
 85 |      */
 86 |     public CheaperCharBuffer(final int startSize, final int growBy) {
 87 |         this.data_ = new char[startSize];
 88 |         this.length_ = 0;
 89 |         this.growBy_ = Math.max(1, growBy);
 90 |     }
 91 | 
 92 |     /**
 93 |      * Constructs an XMLCharBuffer from another buffer. Copies the data
 94 |      * over. The new buffer capacity matches the length of the source.
 95 |      *
 96 |      * @param src the source buffer to copy from
 97 |      */
 98 |     public CheaperCharBuffer(final CheaperCharBuffer src) {
 99 |         this(src, 0);
100 |     }
101 | 
102 |     /**
103 |      * Constructs an XMLCharBuffer from another buffer. Copies the data
104 |      * over. You can add more capacity on top of the source length. If
105 |      * you specify 0, the capacity will match the src length.
106 |      *
107 |      * @param src the source buffer to copy from
108 |      * @param addCapacity how much capacity to add to origin length
109 |      */
110 |     public CheaperCharBuffer(final CheaperCharBuffer src, final int addCapacity) {
111 |         this.data_ = Arrays.copyOf(src.data_, src.length_ + Math.max(0, addCapacity));
112 |         this.length_ = src.length();
113 |         this.growBy_ = Math.max(1, CAPACITY_GROWTH);
114 |     }
115 | 
116 |     /**
117 |      * Constructs an XMLCharBuffer from a string. To avoid
118 |      * too much allocation, we just take the string array as is and
119 |      * don't allocate extra space in the first place.
120 |      *
121 |      * @param src the string to copy from
122 |      */
123 |     public CheaperCharBuffer(final String src) {
124 |         this.data_ = src.toCharArray();
125 |         this.length_ = src.length();
126 |         this.growBy_ = CAPACITY_GROWTH;
127 |     }
128 | 
129 |     /**
130 |      * Constructs an XMLString structure preset with the specified values.
131 |      * There will not be any room to grow, if you need that, construct an
132 |      * empty one and append.
133 |      *
134 |      * <p>There are not range checks performed. Make sure your data is correct.
135 |      *
136 |      * @param ch     The character array, must not be null
137 |      * @param offset The offset into the character array.
138 |      * @param length The length of characters from the offset.
139 |      */
140 |     public CheaperCharBuffer(final char[] ch, final int offset, final int length) {
141 |         // just as big as we need it
142 |         this(length);
143 |         append(ch, offset, length);
144 |     }
145 | 
146 |     /**
147 |      * Check capacity and grow if needed automatically
148 |      *
149 |      * @param minimumCapacity how much space do we need at least
150 |      */
151 |     private void ensureCapacity(final int minimumCapacity) {
152 |         if (minimumCapacity > this.data_.length) {
153 |             final int newSize = Math.max(minimumCapacity + this.growBy_, (this.data_.length << 1) + 2);
154 |             this.data_ = Arrays.copyOf(this.data_, newSize);
155 |         }
156 |     }
157 | 
158 |     /**
159 |      * Returns the current max capacity without growth. Does not
160 |      * indicate how much capacity is already in use. Use {@link #length()}
161 |      * for that.
162 |      *
163 |      * @return the current capacity, not taken any usage into account
164 |      */
165 |     public int capacity() {
166 |         return this.data_.length;
167 |     }
168 | 
169 |     /**
170 |      * Appends a single character to the buffer.
171 |      *
172 |      * @param c the character to append
173 |      * @return this instance
174 |      */
175 |     public CheaperCharBuffer append(final char c) {
176 |         final int oldLength = this.length_++;
177 | 
178 |         // ensureCapacity is not inlined by the compiler, so put that here for the most
179 |         // called method of all appends. Duplicate code, but for a reason.
180 |         if (oldLength == this.data_.length) {
181 |             final int newSize = Math.max(oldLength + this.growBy_, (this.data_.length << 1) + 2);
182 |             this.data_ = Arrays.copyOf(this.data_, newSize);
183 |         }
184 | 
185 |         this.data_[oldLength] = c;
186 | 
187 |         return this;
188 |     }
189 | 
190 |     /**
191 |      * Append a string to this buffer without copying the string first.
192 |      *
193 |      * @param src the string to append
194 |      * @return this instance
195 |      */
196 |     public CheaperCharBuffer append(final String src) {
197 |         final int start = this.length_;
198 |         this.length_ = this.length_ + src.length();
199 |         ensureCapacity(this.length_);
200 | 
201 |         // copy char by char because we don't get a copy for free
202 |         // from a string yet, this might change when immutable arrays
203 |         // make it into Java, but that will not be very soon
204 |         for (int i = 0; i < src.length(); i++) {
205 |             this.data_[start + i] = src.charAt(i);
206 |         }
207 | 
208 |         return this;
209 |     }
210 | 
211 |     /**
212 |      * Add another buffer to this one.
213 |      *
214 |      * @param src the buffer to append
215 |      * @return this instance
216 |      */
217 |     public CheaperCharBuffer append(final CheaperCharBuffer src) {
218 |         final int start = this.length_;
219 |         this.length_ = this.length_ + src.length();
220 |         ensureCapacity(this.length_);
221 | 
222 |         System.arraycopy(src.data_, 0, this.data_, start, src.length_);
223 | 
224 |         return this;
225 |     }
226 | 
227 |     /**
228 |      * Add data from a char array to this buffer with the ability to specify
229 |      * a range to copy from
230 |      *
231 |      * @param src the source char array
232 |      * @param offset the pos to start to copy from
233 |      * @param length the length of the data to copy
234 |      *
235 |      * @return this instance
236 |      */
237 |     public CheaperCharBuffer append(final char[] src, final int offset, final int length) {
238 |         final int start = this.length_;
239 |         this.length_ = start + length;
240 | 
241 |         ensureCapacity(this.length_);
242 | 
243 |         System.arraycopy(src, offset, this.data_, start, length);
244 | 
245 |         return this;
246 |     }
247 | 
248 |     /**
249 |      * Returns the current length
250 |      *
251 |      * @return the length of the charbuffer data
252 |      */
253 |     public int length() {
254 |         return length_;
255 |     }
256 | 
257 |     /**
258 |      * Tell us how much the capacity grows if needed
259 |      *
260 |      * @return the value that determines how much we grow the backing
261 |      *      array in case we have to
262 |      */
263 |     public int getGrowBy() {
264 |         return this.growBy_;
265 |     }
266 | 
267 |     /**
268 |      * Resets the buffer to 0 length. It won't resize it to avoid memory
269 |      * churn.
270 |      *
271 |      * @return this instance for fluid programming
272 |      */
273 |     public CheaperCharBuffer clear() {
274 |         this.length_ = 0;
275 | 
276 |         return this;
277 |     }
278 | 
279 |     /**
280 |      * Resets the buffer to 0 length and sets the new data. This
281 |      * is a little cheaper than clear().append(c) depending on
282 |      * the where  and the inlining decisions.
283 |      *
284 |      * @param c the char to set
285 |      * @return this instance for fluid programming
286 |      */
287 |     public CheaperCharBuffer clearAndAppend(final char c) {
288 |         this.length_ = 0;
289 | 
290 |         if (this.data_.length > 0) {
291 |             this.data_[this.length_] = c;
292 |             this.length_++;
293 |         }
294 |         else {
295 |             // the rare case when we don't have any buffer at hand
296 |             append(c);
297 |         }
298 | 
299 |         return this;
300 |     }
301 | 
302 |     /**
303 |      * Does this buffer end with this string? If we check for
304 |      * the empty string, we get true. If we would support JDK 11, we could
305 |      * use Arrays.mismatch and be way faster.
306 |      *
307 |      * @param s the string to check the end against
308 |      * @return true of the end matches the buffer, false otherwise
309 |      */
310 |     public boolean endsWith(final String s) {
311 |         // length does not match, cannot be the end
312 |         if (this.length_ < s.length()) {
313 |             return false;
314 |         }
315 | 
316 |         // check the string by each char, avoids a copy of the string
317 |         final int start = this.length_ - s.length();
318 | 
319 |         // change this to Arrays.mismatch when going JDK 11 or higher
320 |         for (int i = 0; i < s.length(); i++) {
321 |             if (this.data_[i + start] != s.charAt(i)) {
322 |                 return false;
323 |             }
324 |         }
325 | 
326 |         return true;
327 |     }
328 | 
329 |     /**
330 |      * Reduces the buffer to the content between start and end marker when
331 |      * only whitespaces are found before the startMarker as well as after the end marker.
332 |      * If both strings overlap due to identical characters such as "foo" and "oof"
333 |      * and the buffer is " foof ", we don't do anything.
334 |      *
335 |      * <p>If a marker is empty, it behaves like {@link java.lang.String#trim()} on that side.
336 |      *
337 |      * @param startMarker the start string to find, must not be null
338 |      * @param endMarker the end string to find, must not be null
339 |      * @return this instance
340 |      *
341 |      * @deprecated Use the new method {@link #trimToContent(String, String)} instead.
342 |      */
343 |     public CheaperCharBuffer reduceToContent(final String startMarker, final String endMarker) {
344 |         return trimToContent(startMarker, endMarker);
345 |     }
346 | 
347 |     /**
348 |      * Reduces the buffer to the content between start and end marker when
349 |      * only whitespaces are found before the startMarker as well as after the end marker.
350 |      * If both strings overlap due to identical characters such as "foo" and "oof"
351 |      * and the buffer is " foof ", we don't do anything.
352 |      *
353 |      * <p>If a marker is empty, it behaves like {@link java.lang.String#trim()} on that side.
354 |      *
355 |      * @param startMarker the start string to find, must not be null
356 |      * @param endMarker the end string to find, must not be null
357 |      * @return this instance
358 |      */
359 |     public CheaperCharBuffer trimToContent(final String startMarker, final String endMarker) {
360 |         // if both are longer or same length than content, don't do anything
361 |         final int markerLength = startMarker.length() + endMarker.length();
362 |         if (markerLength >= this.length_) {
363 |             return this;
364 |         }
365 | 
366 |         // run over starting whitespaces
367 |         int sPos = 0;
368 |         for (; sPos < this.length_ - markerLength; sPos++) {
369 |             if (!Character.isWhitespace(this.data_[sPos])) {
370 |                 break;
371 |             }
372 |         }
373 | 
374 |         // run over ending whitespaces
375 |         int ePos = this.length_ - 1;
376 |         for (; ePos > sPos - markerLength; ePos--) {
377 |             if (!Character.isWhitespace(this.data_[ePos])) {
378 |                 break;
379 |             }
380 |         }
381 | 
382 |         // if we have less content than marker length, give up
383 |         // this also helps when markers overlap such as
384 |         // <!-- and --> and the string is " <!---> "
385 |         if (ePos - sPos + 1 < markerLength) {
386 |             return this;
387 |         }
388 | 
389 |         // check the start
390 |         for (int i = 0; i < startMarker.length(); i++) {
391 |             if (startMarker.charAt(i) != this.data_[i + sPos]) {
392 |                 // no start match, stop and don't do anything
393 |                 return this;
394 |             }
395 |         }
396 | 
397 |         // check the end, ePos is when the first good char
398 |         // occurred
399 |         final int endStartCheckPos = ePos - endMarker.length() + 1;
400 |         for (int i = 0; i < endMarker.length(); i++) {
401 |             if (endMarker.charAt(i) != this.data_[endStartCheckPos + i]) {
402 |                 // no start match, stop and don't do anything
403 |                 return this;
404 |             }
405 |         }
406 | 
407 |         // shift left and cut length
408 |         final int newLength = ePos - sPos + 1 - markerLength;
409 |         System.arraycopy(this.data_,
410 |                 sPos + startMarker.length(),
411 |                 this.data_,
412 |                 0, newLength);
413 |         this.length_ = newLength;
414 | 
415 |         return this;
416 |     }
417 | 
418 |     /**
419 |      * Check if we have only whitespaces
420 |      *
421 |      * @return true if we have only whitespace, false otherwise
422 |      */
423 |     public boolean isWhitespace() {
424 |         for (int i = 0; i < this.length_; i++) {
425 |             if (!Character.isWhitespace(this.data_[i])) {
426 |                 return false;
427 |             }
428 |         }
429 |         return true;
430 |     }
431 | 
432 |     /**
433 |      * Trims the string similar to {@link java.lang.String#trim()}
434 |      *
435 |      * @return a string with removed whitespace at the beginning and the end
436 |      */
437 |     public CheaperCharBuffer trim() {
438 |         // clean the end first, because it is cheap
439 |         return trimTrailing().trimLeading();
440 |     }
441 | 
442 |     /**
443 |      * Removes all whitespace before the first non-whitespace char.
444 |      * If all are whitespaces, we get an empty buffer
445 |      *
446 |      * @return this instance
447 |      */
448 |     public CheaperCharBuffer trimLeading() {
449 |         // run over starting whitespace
450 |         int sPos = 0;
451 |         for (; sPos < this.length_; sPos++) {
452 |             if (!Character.isWhitespace(this.data_[sPos])) {
453 |                 break;
454 |             }
455 |         }
456 | 
457 |         if (sPos == 0) {
458 |             // nothing to do
459 |             return this;
460 |         }
461 |         else if (sPos == this.length_) {
462 |             // only whitespace
463 |             this.length_ = 0;
464 |             return this;
465 |         }
466 | 
467 |         // shift left
468 |         final int newLength = this.length_ - sPos;
469 |         System.arraycopy(this.data_,
470 |                 sPos,
471 |                 this.data_,
472 |                 0, newLength);
473 |         this.length_ = newLength;
474 | 
475 |         return this;
476 |     }
477 | 
478 |     /**
479 |      * Removes all whitespace at the end.
480 |      * If all are whitespace, we get an empty buffer
481 |      *
482 |      * @return this instance
483 |      *
484 |      * @deprecated Use {@link #trimTrailing()} instead.
485 |      */
486 |     public CheaperCharBuffer trimWhitespaceAtEnd() {
487 |         return trimTrailing();
488 |     }
489 | 
490 |     /**
491 |      * Removes all whitespace at the end.
492 |      * If all are whitespace, we get an empty buffer
493 |      *
494 |      * @return this instance
495 |      */
496 |     public CheaperCharBuffer trimTrailing() {
497 |         // run over ending whitespaces
498 |         int ePos = this.length_ - 1;
499 |         for (; ePos >= 0; ePos--) {
500 |             if (!Character.isWhitespace(this.data_[ePos])) {
501 |                 break;
502 |             }
503 |         }
504 | 
505 |         this.length_ = ePos + 1;
506 | 
507 |         return this;
508 |     }
509 | 
510 |     /**
511 |      * Shortens the buffer by that many positions. If the count is
512 |      * larger than the length, we get just an empty buffer. If you pass in negative
513 |      * values, we are failing, likely often silently. It is all about performance and
514 |      * not a general all-purpose API.
515 |      *
516 |      * @param count a positive number, no runtime checks, if count is larger than
517 |      *      length, we get length = 0
518 |      * @return this instance
519 |      */
520 |     public CheaperCharBuffer shortenBy(final int count) {
521 |         final int newLength = this.length_ - count;
522 |         this.length_ = newLength < 0 ? 0 : newLength;
523 | 
524 |         return this;
525 |     }
526 | 
527 |     /**
528 |      * Get the characters as char array, this will be a copy!
529 |      *
530 |      * @return a copy of the underlying char darta
531 |      */
532 |     public char[] getChars() {
533 |         return Arrays.copyOf(this.data_, this.length_);
534 |     }
535 | 
536 |     /**
537 |      * Returns a string representation of this buffer. This will be a copy
538 |      * operation. If the buffer is emoty, we get a constant empty String back
539 |      * to avoid any overhead.
540 |      *
541 |      * @return a string of the content of this buffer
542 |      */
543 |     @Override
544 |     public String toString() {
545 |         if (this.length_ > 0) {
546 |             return new String(this.data_, 0, this.length_);
547 |         }
548 |         else {
549 |             return "";
550 |         }
551 |     }
552 | 
553 |     /**
554 |      * Returns the char a the given position. Will complain if
555 |      * we try to read outside the range. We do a range check here
556 |      * because we might not notice when we are within the buffer
557 |      * but outside the current length.
558 |      *
559 |      * @param index the position to read from
560 |      * @return the char at the position
561 |      * @throws IndexOutOfBoundsException
562 |      *      in case one tries to read outside of valid buffer range
563 |      */
564 |     @Override
565 |     public char charAt(final int index) {
566 |         if (index > this.length_ - 1 || index < 0) {
567 |             throw new IndexOutOfBoundsException(
568 |                     "Tried to read outside of the valid buffer data");
569 |         }
570 | 
571 |         return this.data_[index];
572 |     }
573 | 
574 |     /**
575 |      * Returns the char at the given position. No checks are
576 |      * performed. It is up to the caller to make sure we
577 |      * read correctly. Reading outside of the array will
578 |      * cause an {@link IndexOutOfBoundsException} but using an
579 |      * incorrect position in the array (such as beyond length)
580 |      * might stay unnoticed! This is a performance method,
581 |      * use at your own risk.
582 |      *
583 |      * @param index the position to read from
584 |      * @return the char at the position
585 |      */
586 |     public char unsafeCharAt(final int index) {
587 |         return this.data_[index];
588 |     }
589 | 
590 |     /**
591 |      * Returns a content copy of this buffer
592 |      *
593 |      * @return a copy of this buffer, the capacity might differ
594 |      */
595 |     @Override
596 |     public CheaperCharBuffer clone() {
597 |         return new CheaperCharBuffer(this);
598 |     }
599 | 
600 |     /**
601 |      * Returns a <code>CharSequence</code> that is a subsequence of this sequence.
602 |      * The subsequence starts with the <code>char</code> value at the specified index and
603 |      * ends with the <code>char</code> value at index <tt>end - 1</tt>.  The length
604 |      * (in <code>char</code>s) of the
605 |      * returned sequence is <tt>end - start</tt>, so if <tt>start == end</tt>
606 |      * then an empty sequence is returned.
607 |      *
608 |      * @param   start   the start index, inclusive
609 |      * @param   end     the end index, exclusive
610 |      *
611 |      * @return  the specified subsequence
612 |      *
613 |      * @throws  IndexOutOfBoundsException
614 |      *          if <tt>start</tt> or <tt>end</tt> are negative,
615 |      *          if <tt>end</tt> is greater than <tt>length()</tt>,
616 |      *          or if <tt>start</tt> is greater than <tt>end</tt>
617 |      *
618 |      * @return a charsequence of this buffer
619 |      */
620 |     @Override
621 |     public CharSequence subSequence(final int start, final int end) {
622 |         if (start < 0) {
623 |             throw new StringIndexOutOfBoundsException(start);
624 |         }
625 |         if (end > this.length_) {
626 |             throw new StringIndexOutOfBoundsException(end);
627 |         }
628 | 
629 |         final int l = end - start;
630 |         if (l < 0) {
631 |             throw new StringIndexOutOfBoundsException(l);
632 |         }
633 | 
634 |         return new String(this.data_, start, l);
635 |     }
636 | 
637 |     /**
638 |      * Two buffers are identical when the length and
639 |      * the content of the backing array (only for the
640 |      * data in view) are identical.
641 |      *
642 |      * @param o the object to compare with
643 |      * @return true if length and array content match, false otherwise
644 |      */
645 |     @Override
646 |     public boolean equals(final Object o) {
647 |         if (o instanceof CharSequence) {
648 |             final CharSequence ob = (CharSequence) o;
649 | 
650 |             if (ob.length() != this.length_) {
651 |                 return false;
652 |             }
653 | 
654 |             // ok, in JDK 11 or up, we could use an
655 |             // Arrays.mismatch, but we cannot do that
656 |             // due to JDK 8 compatibility
657 |             for (int i = 0; i < this.length_; i++) {
658 |                 if (ob.charAt(i) != this.data_[i]) {
659 |                     return false;
660 |                 }
661 |             }
662 | 
663 |             // length and content match, be happy
664 |             return true;
665 |         }
666 | 
667 |         return false;
668 |     }
669 | 
670 |     /**
671 |      * We don't cache the hashcode because we mutate often. Don't use this in
672 |      * hashmaps as key. But you can use that to look up in a hashmap against
673 |      * a string using the CharSequence interface.
674 |      *
675 |      * @return the hashcode, similar to what a normal string would deliver
676 |      */
677 |     @Override
678 |     public int hashCode() {
679 |         int h = 0;
680 | 
681 |         for (int i = 0; i < this.length_; i++) {
682 |             h = ((h << 5) - h) + this.data_[i];
683 |         }
684 | 
685 |         return h;
686 |     }
687 | 
688 |     /**
689 |      * Append a character to an XMLCharBuffer. The character is an int value, and
690 |      * can either be a single UTF-16 character or a supplementary character
691 |      * represented by two UTF-16 code points.
692 |      *
693 |      * @param value The character value.
694 |      * @return this instance for fluid programming
695 |      *
696 |      * @throws IllegalArgumentException if the specified
697 |      *          {@code codePoint} is not a valid Unicode code point.
698 |      */
699 |     public CheaperCharBuffer appendCodePoint(final int value) {
700 |         if (value <= Character.MAX_VALUE) {
701 |             return this.append((char) value);
702 |         }
703 |         else {
704 |             try {
705 |                 final char[] chars = Character.toChars(value);
706 |                 return this.append(chars, 0, chars.length);
707 |             }
708 |             catch (final IllegalArgumentException e) {
709 |                 // when value is not valid as UTF-16
710 |                 this.append(REPLACEMENT_CHARACTER);
711 |                 throw e;
712 |             }
713 |         }
714 |     }
715 | }
716 | 


--------------------------------------------------------------------------------
/src/main/java/org/rschwietzke/FastRandom.java:
--------------------------------------------------------------------------------
 1 | /*
 2 |  *  Copyright 2023 The original authors
 3 |  *
 4 |  *  Licensed under the Apache License, Version 2.0 (the "License");
 5 |  *  you may not use this file except in compliance with the License.
 6 |  *  You may obtain a copy of the License at
 7 |  *
 8 |  *      http://www.apache.org/licenses/LICENSE-2.0
 9 |  *
10 |  *  Unless required by applicable law or agreed to in writing, software
11 |  *  distributed under the License is distributed on an "AS IS" BASIS,
12 |  *  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
13 |  *  See the License for the specific language governing permissions and
14 |  *  limitations under the License.
15 |  */
16 | package org.rschwietzke;
17 | 
18 | /**
19 |  * Ultra-fast pseudo random generator that is not synchronized!
20 |  * Don't use anything from Random by inheritance, this will inherit
21 |  * a volatile! Not my idea, copyied in parts some demo random
22 |  * generator lessons.
23 |  *
24 |  * @author rschwietzke
25 |  *
26 |  */
27 | public class FastRandom {
28 |     private long seed;
29 | 
30 |     public FastRandom() {
31 |         this.seed = System.currentTimeMillis();
32 |     }
33 | 
34 |     public FastRandom(long seed) {
35 |         this.seed = seed;
36 |     }
37 | 
38 |     protected int next(int nbits) {
39 |         // N.B. Not thread-safe!
40 |         long x = this.seed;
41 |         x ^= (x << 21);
42 |         x ^= (x >>> 35);
43 |         x ^= (x << 4);
44 |         this.seed = x;
45 | 
46 |         x &= ((1L << nbits) - 1);
47 | 
48 |         return (int) x;
49 |     }
50 | 
51 |     /**
52 |      * Borrowed from the JDK
53 |      *
54 |      * @param bound
55 |      * @return
56 |      */
57 |     public int nextInt(int bound) {
58 |         int r = next(31);
59 |         int m = bound - 1;
60 |         if ((bound & m) == 0) // i.e., bound is a power of 2
61 |             r = (int) ((bound * (long) r) >> 31);
62 |         else {
63 |             for (int u = r; u - (r = u % bound) + m < 0; u = next(31))
64 |                 ;
65 |         }
66 |         return r;
67 |     }
68 | 
69 |     /**
70 |      * Borrowed from the JDK
71 |      * @return
72 |      */
73 |     public int nextInt() {
74 |         return next(32);
75 |     }
76 | }
77 | 


--------------------------------------------------------------------------------
/src/main/nodejs/Edgar-P-yan/.gitignore:
--------------------------------------------------------------------------------
  1 | # Based on https://raw.githubusercontent.com/github/gitignore/main/Node.gitignore
  2 | 
  3 | # Logs
  4 | 
  5 | logs
  6 | _.log
  7 | npm-debug.log_
  8 | yarn-debug.log*
  9 | yarn-error.log*
 10 | lerna-debug.log*
 11 | .pnpm-debug.log*
 12 | 
 13 | # Caches 
 14 | 
 15 | .cache
 16 | 
 17 | # Diagnostic reports (https://nodejs.org/api/report.html)
 18 | 
 19 | report.[0-9]_.[0-9]_.[0-9]_.[0-9]_.json
 20 | 
 21 | # Runtime data
 22 | 
 23 | pids
 24 | _.pid
 25 | _.seed
 26 | *.pid.lock
 27 | 
 28 | # Directory for instrumented libs generated by jscoverage/JSCover
 29 | 
 30 | lib-cov
 31 | 
 32 | # Coverage directory used by tools like istanbul
 33 | 
 34 | coverage
 35 | *.lcov
 36 | 
 37 | # nyc test coverage
 38 | 
 39 | .nyc_output
 40 | 
 41 | # Grunt intermediate storage (https://gruntjs.com/creating-plugins#storing-task-files)
 42 | 
 43 | .grunt
 44 | 
 45 | # Bower dependency directory (https://bower.io/)
 46 | 
 47 | bower_components
 48 | 
 49 | # node-waf configuration
 50 | 
 51 | .lock-wscript
 52 | 
 53 | # Compiled binary addons (https://nodejs.org/api/addons.html)
 54 | 
 55 | build/Release
 56 | 
 57 | # Dependency directories
 58 | 
 59 | node_modules/
 60 | jspm_packages/
 61 | 
 62 | # Snowpack dependency directory (https://snowpack.dev/)
 63 | 
 64 | web_modules/
 65 | 
 66 | # TypeScript cache
 67 | 
 68 | *.tsbuildinfo
 69 | 
 70 | # Optional npm cache directory
 71 | 
 72 | .npm
 73 | 
 74 | # Optional eslint cache
 75 | 
 76 | .eslintcache
 77 | 
 78 | # Optional stylelint cache
 79 | 
 80 | .stylelintcache
 81 | 
 82 | # Microbundle cache
 83 | 
 84 | .rpt2_cache/
 85 | .rts2_cache_cjs/
 86 | .rts2_cache_es/
 87 | .rts2_cache_umd/
 88 | 
 89 | # Optional REPL history
 90 | 
 91 | .node_repl_history
 92 | 
 93 | # Output of 'npm pack'
 94 | 
 95 | *.tgz
 96 | 
 97 | # Yarn Integrity file
 98 | 
 99 | .yarn-integrity
100 | 
101 | # dotenv environment variable files
102 | 
103 | .env
104 | .env.development.local
105 | .env.test.local
106 | .env.production.local
107 | .env.local
108 | 
109 | # parcel-bundler cache (https://parceljs.org/)
110 | 
111 | .parcel-cache
112 | 
113 | # Next.js build output
114 | 
115 | .next
116 | out
117 | 
118 | # Nuxt.js build / generate output
119 | 
120 | .nuxt
121 | dist
122 | 
123 | # Gatsby files
124 | 
125 | # Comment in the public line in if your project uses Gatsby and not Next.js
126 | 
127 | # https://nextjs.org/blog/next-9-1#public-directory-support
128 | 
129 | # public
130 | 
131 | # vuepress build output
132 | 
133 | .vuepress/dist
134 | 
135 | # vuepress v2.x temp and cache directory
136 | 
137 | .temp
138 | 
139 | # Docusaurus cache and generated files
140 | 
141 | .docusaurus
142 | 
143 | # Serverless directories
144 | 
145 | .serverless/
146 | 
147 | # FuseBox cache
148 | 
149 | .fusebox/
150 | 
151 | # DynamoDB Local files
152 | 
153 | .dynamodb/
154 | 
155 | # TernJS port file
156 | 
157 | .tern-port
158 | 
159 | # Stores VSCode versions used for testing VSCode extensions
160 | 
161 | .vscode-test
162 | 
163 | # yarn v2
164 | 
165 | .yarn/cache
166 | .yarn/unplugged
167 | .yarn/build-state.yml
168 | .yarn/install-state.gz
169 | .pnp.*
170 | 
171 | # IntelliJ based IDEs
172 | .idea
173 | 
174 | # Finder (MacOS) folder config
175 | .DS_Store
176 | 


--------------------------------------------------------------------------------
/src/main/nodejs/Edgar-P-yan/README.md:
--------------------------------------------------------------------------------
 1 | # 1brc Node.js by [@Edgar-P-yan](https://github.com/Edgar-P-yan)
 2 | 
 3 | ## Details:
 4 | 
 5 | - Machine: MacBook Pro M1 Max 32GB;
 6 | - Best results I could get with **Node.js is 23s**;
 7 | - Utilizes all cores of the system (10 on mine) via worker threads;
 8 | - A custom input-specific and quite fast float point to integer parser;
 9 | - Byte-by-byte processing of the whole file;
10 | - Statically typed code that gets JITed very efficiently;
11 | 
12 | ## What should be improved:
13 | 
14 | - Custom hashmap with 2-byte hashes. Right now I just use the builtin `Map`, which is too general purpose for this task, hence quite slow, around 30% of spent time is on the Map.
15 | - Set higher watermarks for the GC, it might save some milliseconds too.
16 | - Do fewer allocations. Right now for each station name in each row a new string gets allocated.
17 | 


--------------------------------------------------------------------------------
/src/main/nodejs/Edgar-P-yan/index.js:
--------------------------------------------------------------------------------
  1 | import * as os from 'node:os';
  2 | import * as fsp from 'node:fs/promises';
  3 | import * as fs from 'node:fs';
  4 | import * as workerThreads from 'worker_threads';
  5 | 
  6 | const MAX_LINE_LENGTH = 100 + 1 + 4 + 1;
  7 | const CHAR_SEMICOLON = ';'.charCodeAt(0);
  8 | const CHAR_NEWLINE = '\n'.charCodeAt(0);
  9 | const TOKEN_STATION_NAME = 0;
 10 | const TOKEN_TEMPERATURE = 1;
 11 | 
 12 | /** @type {(...args: any[]) => void} */
 13 | const debug = process.env.DEBUG
 14 |   ? (...args) => console.error(`Thread ${workerThreads.threadId}:`, args)
 15 |   : () => {};
 16 | 
 17 | /**
 18 |  * @typedef {Map<string, {min: number, max: number, sum: number, count: number}>} CalcResultsCont
 19 |  */
 20 | 
 21 | if (workerThreads.isMainThread) {
 22 |   const fileName = process.argv[2];
 23 | 
 24 |   const file = await fsp.open(fileName);
 25 | 
 26 |   const size = (await file.stat()).size;
 27 | 
 28 |   const threadsCount = os.cpus().length;
 29 | 
 30 |   const chunkSize = Math.floor(size / threadsCount);
 31 | 
 32 |   /** @type {number[]} */
 33 |   const chunkOffsets = [];
 34 | 
 35 |   let offset = 0;
 36 |   const bufFindNl = Buffer.alloc(MAX_LINE_LENGTH);
 37 | 
 38 |   while (true) {
 39 |     offset += chunkSize;
 40 | 
 41 |     if (offset >= size) {
 42 |       chunkOffsets.push(size);
 43 |       break;
 44 |     }
 45 | 
 46 |     await file.read(bufFindNl, 0, MAX_LINE_LENGTH, offset);
 47 | 
 48 |     const nlPos = bufFindNl.indexOf(10);
 49 |     bufFindNl.fill(0);
 50 | 
 51 |     if (nlPos === -1) {
 52 |       chunkOffsets.push(size);
 53 |       break;
 54 |     } else {
 55 |       offset += nlPos + 1;
 56 |       chunkOffsets.push(offset);
 57 |     }
 58 |   }
 59 | 
 60 |   await file.close();
 61 | 
 62 |   /**
 63 |    * @type {CalcResultsCont}
 64 |    */
 65 |   const compiledResults = new Map();
 66 | 
 67 |   let stoppedWorkers = 0;
 68 | 
 69 |   for (let i = 0; i < chunkOffsets.length; i++) {
 70 |     const worker = new workerThreads.Worker(
 71 |       new URL(import.meta.resolve('./index.js')),
 72 |       {
 73 |         workerData: {
 74 |           fileName,
 75 |           start: i === 0 ? 0 : chunkOffsets[i - 1],
 76 |           end: chunkOffsets[i],
 77 |         },
 78 |       }
 79 |     );
 80 | 
 81 |     worker.on(
 82 |       'message',
 83 |       (
 84 |         /** @type {CalcResultsCont} */
 85 |         message
 86 |       ) => {
 87 |         for (let [key, value] of message.entries()) {
 88 |           const existing = compiledResults.get(key);
 89 |           if (existing) {
 90 |             existing.min = Math.min(existing.min, value.min);
 91 |             existing.max = Math.max(existing.max, value.max);
 92 |             existing.sum += value.sum;
 93 |             existing.count += value.count;
 94 |           } else {
 95 |             compiledResults.set(key, value);
 96 |           }
 97 |         }
 98 |       }
 99 |     );
100 | 
101 |     worker.on('error', (err) => {
102 |       console.error(err);
103 |     });
104 | 
105 |     worker.on('exit', (code) => {
106 |       if (code !== 0) {
107 |         new Error(`Worker stopped with exit code ${code}`);
108 |       } else {
109 |         debug('Worker stopped');
110 |       }
111 | 
112 |       stoppedWorkers++;
113 | 
114 |       if (stoppedWorkers === chunkOffsets.length) {
115 |         printCompiledResults(compiledResults);
116 |       }
117 |     });
118 |   }
119 | } else {
120 |   const { fileName, start, end } = workerThreads.workerData;
121 |   if (start > end - 1) {
122 |     workerThreads.parentPort.postMessage(new Map());
123 |   } else {
124 |     const readStream = fs.createReadStream(fileName, {
125 |       start: start,
126 |       end: end - 1,
127 |     });
128 | 
129 |     parseStream(readStream);
130 |   }
131 | }
132 | 
133 | /**
134 |  * @param {CalcResultsCont} compiledResults
135 |  */
136 | function printCompiledResults(compiledResults) {
137 |   const sortedStations = Array.from(compiledResults.keys()).sort();
138 | 
139 |   process.stdout.write('{');
140 |   for (let i = 0; i < sortedStations.length; i++) {
141 |     if (i > 0) {
142 |       process.stdout.write(', ');
143 |     }
144 |     const data = compiledResults.get(sortedStations[i]);
145 |     process.stdout.write(sortedStations[i]);
146 |     process.stdout.write('=');
147 |     process.stdout.write(
148 |       round(data.min / 10) +
149 |         '/' +
150 |         round(data.sum / 10 / data.count) +
151 |         '/' +
152 |         round(data.max / 10)
153 |     );
154 |   }
155 |   process.stdout.write('}\n');
156 | }
157 | 
158 | /**
159 |  * @example
160 |  * round(1.2345) // "1.2"
161 |  * round(1.55) // "1.6"
162 |  * round(1) // "1.0"
163 |  *
164 |  * @param {number} num
165 |  * @returns {string}
166 |  */
167 | function round(num) {
168 |   const fixed = Math.round(10 * num) / 10;
169 | 
170 |   return fixed.toFixed(1);
171 | }
172 | 
173 | /**
174 |  * @param {import('node:fs').ReadStream} readStream
175 |  */
176 | function parseStream(readStream) {
177 |   let readingToken = TOKEN_STATION_NAME;
178 | 
179 |   let stationName = Buffer.allocUnsafe(100);
180 |   let stationNameLen = 0;
181 | 
182 |   let temperature = Buffer.allocUnsafe(5);
183 |   let temperatureLen = 0;
184 | 
185 |   /**
186 |    * @type {CalcResultsCont}
187 |    */
188 |   const map = new Map();
189 | 
190 |   /**
191 |    * @param {Buffer} chunk
192 |    * @returns {void}
193 |    */
194 |   function parseChunk(chunk) {
195 |     for (let i = 0; i < chunk.length; i++) {
196 |       if (chunk[i] === CHAR_SEMICOLON) {
197 |         readingToken = TOKEN_TEMPERATURE;
198 |       } else if (chunk[i] === CHAR_NEWLINE) {
199 |         const stationNameStr = stationName.toString('utf8', 0, stationNameLen);
200 | 
201 |         let temperatureFloat = 0 | 0;
202 |         try {
203 |           temperatureFloat = parseFloatBufferIntoInt(
204 |             temperature,
205 |             temperatureLen
206 |           );
207 |         } catch (err) {
208 |           console.log({ temperature, temperatureLen }, err.message);
209 |           throw err;
210 |         }
211 | 
212 |         const existing = map.get(stationNameStr);
213 | 
214 |         if (existing) {
215 |           existing.min =
216 |             existing.min < temperatureFloat ? existing.min : temperatureFloat;
217 |           existing.max =
218 |             existing.max > temperatureFloat ? existing.max : temperatureFloat;
219 |           existing.sum += temperatureFloat;
220 |           existing.count++;
221 |         } else {
222 |           map.set(stationNameStr, {
223 |             min: temperatureFloat,
224 |             max: temperatureFloat,
225 |             sum: temperatureFloat,
226 |             count: 1,
227 |           });
228 |         }
229 | 
230 |         readingToken = TOKEN_STATION_NAME;
231 |         stationNameLen = 0;
232 |         temperatureLen = 0;
233 |       } else if (readingToken === TOKEN_STATION_NAME) {
234 |         stationName[stationNameLen] = chunk[i];
235 |         stationNameLen++;
236 |       } else {
237 |         temperature[temperatureLen] = chunk[i];
238 |         temperatureLen++;
239 |       }
240 |     }
241 |   }
242 | 
243 |   readStream.on('data', (/** @type {Buffer} */ chunk) => {
244 |     parseChunk(chunk);
245 |   });
246 | 
247 |   readStream.on('end', () => {
248 |     debug('Sending result to the main thread');
249 |     workerThreads.parentPort.postMessage(map);
250 |   });
251 | }
252 | 
253 | const CHAR_MINUS = '-'.charCodeAt(0);
254 | 
255 | /**
256 |  * @param {Buffer} b
257 |  * @param {number} length 1-5
258 |  *
259 |  * @returns {number}
260 |  */
261 | function parseFloatBufferIntoInt(b, length) {
262 |   if (b[0] === CHAR_MINUS) {
263 |     // b can be -1.1 or -11.1
264 |     switch (length) {
265 |       case 4:
266 |         return -(parseOneDigit(b[1]) * 10 + parseOneDigit(b[3]));
267 |       case 5:
268 |         return -(
269 |           parseOneDigit(b[1]) * 100 +
270 |           parseOneDigit(b[2]) * 10 +
271 |           parseOneDigit(b[4])
272 |         );
273 |     }
274 |   } else {
275 |     // b can be 1.1 or 11.1
276 |     switch (length) {
277 |       case 3: // b is 1.1
278 |         return parseOneDigit(b[0]) * 10 + parseOneDigit(b[2]);
279 |       case 4:
280 |         return (
281 |           parseOneDigit(b[0]) * 100 +
282 |           parseOneDigit(b[1]) * 10 +
283 |           parseOneDigit(b[3])
284 |         );
285 |     }
286 |   }
287 | }
288 | 
289 | /**
290 |  * @param {number} char byte number of a digit char
291 |  *
292 |  * @returns {number}
293 |  */
294 | function parseOneDigit(char) {
295 |   return char - 0x30;
296 | }
297 | 


--------------------------------------------------------------------------------
/src/main/nodejs/Edgar-P-yan/package-lock.json:
--------------------------------------------------------------------------------
 1 | {
 2 |   "name": "nodejs",
 3 |   "lockfileVersion": 3,
 4 |   "requires": true,
 5 |   "packages": {
 6 |     "": {
 7 |       "devDependencies": {
 8 |         "@types/node": "^20.10.6"
 9 |       }
10 |     },
11 |     "node_modules/@types/node": {
12 |       "version": "20.10.6",
13 |       "resolved": "https://registry.npmjs.org/@types/node/-/node-20.10.6.tgz",
14 |       "integrity": "sha512-Vac8H+NlRNNlAmDfGUP7b5h/KA+AtWIzuXy0E6OyP8f1tCLYAtPvKRRDJjAPqhpCb0t6U2j7/xqAuLEebW2kiw==",
15 |       "dev": true,
16 |       "dependencies": {
17 |         "undici-types": "~5.26.4"
18 |       }
19 |     },
20 |     "node_modules/undici-types": {
21 |       "version": "5.26.5",
22 |       "resolved": "https://registry.npmjs.org/undici-types/-/undici-types-5.26.5.tgz",
23 |       "integrity": "sha512-JlCMO+ehdEIKqlFxk6IfVoAUVmgz7cU7zD/h9XZ0qzeosSHmUJVOzSQvvYSYWXkFXC+IfLKSIffhv0sVZup6pA==",
24 |       "dev": true
25 |     }
26 |   }
27 | }
28 | 


--------------------------------------------------------------------------------
/src/main/nodejs/Edgar-P-yan/package.json:
--------------------------------------------------------------------------------
1 | {
2 |   "type": "module",
3 |   "module": "es2022",
4 |   "devDependencies": {
5 |     "@types/node": "^20.10.6"
6 |   }
7 | }
8 | 


--------------------------------------------------------------------------------
/src/main/nodejs/Edgar-P-yan/result.txt:
--------------------------------------------------------------------------------
  1 | {Abha=-32.2/18.0/67.2, 
  2 | Abidjan=-23.6/26.0/79.6, 
  3 | Abéché=-22.9/29.4/82.2, 
  4 | Accra=-23.4/26.4/75.5, 
  5 | Addis Ababa=-37.9/16.0/64.6, 
  6 | Adelaide=-32.0/17.3/67.3, 
  7 | Aden=-19.9/29.1/78.7, 
  8 | Ahvaz=-27.1/25.4/77.5, 
  9 | Albuquerque=-35.2/14.0/62.1, 
 10 | Alexandra=-37.9/11.0/57.2, 
 11 | Alexandria=-29.4/20.0/74.8, 
 12 | Algiers=-27.2/18.2/69.4, 
 13 | Alice Springs=-26.7/21.0/67.9, 
 14 | Almaty=-38.9/10.0/63.0, 
 15 | Amsterdam=-39.4/10.2/56.5, 
 16 | Anadyr=-57.3/-6.9/41.9, 
 17 | Anchorage=-48.8/2.8/55.0, 
 18 | Andorra la Vella=-39.4/9.8/60.7, 
 19 | Ankara=-39.0/12.0/68.1, 
 20 | Antananarivo=-31.3/17.9/72.0, 
 21 | Antsiranana=-23.5/25.2/74.0, 
 22 | Arkhangelsk=-49.8/1.3/50.9, 
 23 | Ashgabat=-33.4/17.1/66.0, 
 24 | Asmara=-34.1/15.6/63.6, 
 25 | Assab=-23.3/30.5/85.1, 
 26 | Astana=-50.6/3.5/50.0, 
 27 | Athens=-33.8/19.2/69.8, 
 28 | Atlanta=-33.0/17.0/63.4, 
 29 | Auckland=-37.7/15.2/65.1, 
 30 | Austin=-29.8/20.7/69.2, 
 31 | Baghdad=-28.3/22.8/74.3, 
 32 | Baguio=-32.7/19.5/65.1, 
 33 | Baku=-34.5/15.1/71.7, 
 34 | Baltimore=-39.0/13.1/63.8, 
 35 | Bamako=-26.6/27.8/76.5, 
 36 | Bangkok=-19.9/28.6/76.3, 
 37 | Bangui=-22.6/26.0/75.3, 
 38 | Banjul=-23.6/26.0/76.7, 
 39 | Barcelona=-34.9/18.2/66.8, 
 40 | Bata=-23.0/25.1/73.3, 
 41 | Batumi=-33.2/14.0/65.3, 
 42 | Beijing=-36.0/12.9/66.7, 
 43 | Beirut=-29.0/20.9/72.3, 
 44 | Belgrade=-42.2/12.5/66.3, 
 45 | Belize City=-22.6/26.7/76.2, 
 46 | Benghazi=-29.7/19.9/67.9, 
 47 | Bergen=-41.1/7.7/58.8, 
 48 | Berlin=-36.0/10.3/60.5, 
 49 | Bilbao=-35.8/14.7/62.6, 
 50 | Birao=-26.4/26.5/75.2, 
 51 | Bishkek=-36.5/11.3/58.1, 
 52 | Bissau=-22.3/27.0/82.6, 
 53 | Blantyre=-25.3/22.2/70.2, 
 54 | Bloemfontein=-34.0/15.6/66.5, 
 55 | Boise=-36.9/11.4/60.8, 
 56 | Bordeaux=-37.9/14.2/66.0, 
 57 | Bosaso=-18.7/30.0/79.5, 
 58 | Boston=-37.5/10.9/62.2, 
 59 | Bouaké=-27.5/26.0/86.0, 
 60 | Bratislava=-38.9/10.5/58.6, 
 61 | Brazzaville=-25.9/25.0/73.9, 
 62 | Bridgetown=-21.8/27.0/74.9, 
 63 | Brisbane=-31.1/21.4/68.7, 
 64 | Brussels=-38.3/10.5/58.8, 
 65 | Bucharest=-37.3/10.8/61.2, 
 66 | Budapest=-40.0/11.3/60.7, 
 67 | Bujumbura=-23.4/23.8/71.7, 
 68 | Bulawayo=-28.8/18.9/69.6, 
 69 | Burnie=-35.2/13.1/65.9, 
 70 | Busan=-37.6/15.0/65.7, 
 71 | Cabo San Lucas=-30.6/23.9/80.5, 
 72 | Cairns=-27.0/25.0/81.1, 
 73 | Cairo=-25.5/21.4/74.6, 
 74 | Calgary=-42.7/4.4/57.4, 
 75 | Canberra=-38.4/13.1/67.4, 
 76 | Cape Town=-31.2/16.2/68.7, 
 77 | Changsha=-30.9/17.4/68.5, 
 78 | Charlotte=-35.1/16.1/67.3, 
 79 | Chiang Mai=-23.8/25.8/75.0, 
 80 | Chicago=-41.8/9.8/60.5, 
 81 | Chihuahua=-33.7/18.6/69.5, 
 82 | Chittagong=-24.2/25.9/76.1, 
 83 | Chișinău=-42.4/10.2/63.1, 
 84 | Chongqing=-31.8/18.6/70.8, 
 85 | Christchurch=-39.8/12.2/60.4, 
 86 | City of San Marino=-38.1/11.8/60.8, 
 87 | Colombo=-22.9/27.4/78.0, 
 88 | Columbus=-40.2/11.7/61.0, 
 89 | Conakry=-23.6/26.4/76.8, 
 90 | Copenhagen=-41.4/9.1/57.6, 
 91 | Cotonou=-20.6/27.2/75.9, 
 92 | Cracow=-40.4/9.3/57.1, 
 93 | Da Lat=-34.8/17.9/70.3, 
 94 | Da Nang=-25.6/25.8/81.3, 
 95 | Dakar=-24.6/24.0/74.9, 
 96 | Dallas=-33.1/19.0/68.6, 
 97 | Damascus=-32.9/17.0/67.4, 
 98 | Dampier=-25.4/26.4/77.7, 
 99 | Dar es Salaam=-23.1/25.8/75.4, 
100 | Darwin=-28.0/27.6/76.6, 
101 | Denpasar=-26.6/23.7/73.6, 
102 | Denver=-38.7/10.4/56.8, 
103 | Detroit=-39.3/10.0/60.2, 
104 | Dhaka=-24.8/25.9/76.9, 
105 | Dikson=-60.9/-11.1/38.2, 
106 | Dili=-21.4/26.6/80.8, 
107 | Djibouti=-16.8/29.9/78.8, 
108 | Dodoma=-30.3/22.7/71.5, 
109 | Dolisie=-25.1/24.0/74.8, 
110 | Douala=-22.9/26.7/76.8, 
111 | Dubai=-21.9/26.9/77.4, 
112 | Dublin=-41.0/9.8/59.2, 
113 | Dunedin=-40.5/11.1/61.3, 
114 | Durban=-30.3/20.6/71.9, 
115 | Dushanbe=-31.7/14.7/64.3, 
116 | Edinburgh=-38.7/9.3/59.6, 
117 | Edmonton=-43.6/4.2/51.7, 
118 | El Paso=-33.9/18.1/65.2, 
119 | Entebbe=-29.5/21.0/67.4, 
120 | Erbil=-29.7/19.5/70.3, 
121 | Erzurum=-45.0/5.1/58.3, 
122 | Fairbanks=-49.7/-2.3/51.0, 
123 | Fianarantsoa=-30.8/17.9/66.9, 
124 | Flores, 
125 |  Petén=-21.0/26.4/79.6, 
126 | Frankfurt=-37.1/10.6/60.3, 
127 | Fresno=-33.3/17.9/67.3, 
128 | Fukuoka=-32.2/17.0/66.6, 
129 | Gaborone=-28.3/21.0/69.8, 
130 | Gabès=-29.7/19.5/68.9, 
131 | Gagnoa=-21.4/26.0/76.1, 
132 | Gangtok=-33.4/15.2/67.2, 
133 | Garissa=-20.0/29.3/79.9, 
134 | Garoua=-20.7/28.3/80.3, 
135 | George Town=-27.2/27.9/83.3, 
136 | Ghanzi=-34.3/21.4/67.2, 
137 | Gjoa Haven=-72.4/-14.4/35.4, 
138 | Guadalajara=-29.1/20.9/69.0, 
139 | Guangzhou=-26.5/22.4/72.3, 
140 | Guatemala City=-29.3/20.4/70.7, 
141 | Halifax=-42.1/7.5/58.3, 
142 | Hamburg=-41.4/9.7/57.1, 
143 | Hamilton=-35.1/13.8/64.7, 
144 | Hanga Roa=-31.7/20.5/70.3, 
145 | Hanoi=-28.1/23.6/71.4, 
146 | Harare=-28.7/18.4/66.4, 
147 | Harbin=-46.0/5.0/53.1, 
148 | Hargeisa=-28.8/21.7/72.9, 
149 | Hat Yai=-18.5/27.0/75.4, 
150 | Havana=-29.2/25.2/74.9, 
151 | Helsinki=-39.7/5.9/61.5, 
152 | Heraklion=-30.0/18.9/66.9, 
153 | Hiroshima=-37.7/16.3/65.3, 
154 | Ho Chi Minh City=-28.5/27.4/77.3, 
155 | Hobart=-37.8/12.7/60.7, 
156 | Hong Kong=-24.6/23.3/74.4, 
157 | Honiara=-30.8/26.5/77.2, 
158 | Honolulu=-23.2/25.4/73.4, 
159 | Houston=-26.6/20.8/66.8, 
160 | Ifrane=-36.0/11.4/61.2, 
161 | Indianapolis=-39.5/11.8/61.8, 
162 | Iqaluit=-58.8/-9.3/42.0, 
163 | Irkutsk=-48.6/1.0/53.8, 
164 | Istanbul=-36.7/13.9/64.6, 
165 | Jacksonville=-27.4/20.3/69.8, 
166 | Jakarta=-24.5/26.7/76.7, 
167 | Jayapura=-26.2/27.0/76.1, 
168 | Jerusalem=-33.1/18.3/67.4, 
169 | Johannesburg=-31.8/15.5/66.4, 
170 | Jos=-25.8/22.8/75.0, 
171 | Juba=-18.4/27.8/78.2, 
172 | Kabul=-38.7/12.1/62.4, 
173 | Kampala=-28.2/20.0/68.0, 
174 | Kandi=-19.7/27.7/74.8, 
175 | Kankan=-28.5/26.5/79.6, 
176 | Kano=-26.8/26.4/75.6, 
177 | Kansas City=-37.0/12.5/61.7, 
178 | Karachi=-26.0/26.0/74.2, 
179 | Karonga=-27.4/24.4/79.6, 
180 | Kathmandu=-30.2/18.3/66.6, 
181 | Khartoum=-18.8/29.9/89.3, 
182 | Kingston=-22.7/27.4/76.7, 
183 | Kinshasa=-27.2/25.3/73.9, 
184 | Kolkata=-28.7/26.7/76.4, 
185 | Kuala Lumpur=-25.8/27.3/76.1, 
186 | Kumasi=-22.2/26.0/75.2, 
187 | Kunming=-34.9/15.7/65.3, 
188 | Kuopio=-46.1/3.4/55.1, 
189 | Kuwait City=-25.6/25.7/77.9, 
190 | Kyiv=-49.4/8.4/61.4, 
191 | Kyoto=-31.6/15.8/63.2, 
192 | La Ceiba=-22.3/26.2/77.8, 
193 | La Paz=-25.4/23.7/72.5, 
194 | Lagos=-22.3/26.8/74.4, 
195 | Lahore=-23.8/24.3/72.6, 
196 | Lake Havasu City=-34.1/23.7/70.9, 
197 | Lake Tekapo=-38.9/8.7/59.4, 
198 | Las Palmas de Gran Canaria=-31.1/21.2/68.3, 
199 | Las Vegas=-27.9/20.3/74.3, 
200 | Launceston=-39.2/13.1/60.7, 
201 | Lhasa=-42.5/7.6/55.2, 
202 | Libreville=-22.6/25.9/79.2, 
203 | Lisbon=-33.0/17.5/68.8, 
204 | Livingstone=-27.5/21.8/69.2, 
205 | Ljubljana=-41.4/10.9/58.5, 
206 | Lodwar=-19.0/29.3/78.9, 
207 | Lomé=-23.4/26.9/77.7, 
208 | London=-36.9/11.3/60.8, 
209 | Los Angeles=-28.5/18.6/67.2, 
210 | Louisville=-36.3/13.9/64.6, 
211 | Luanda=-25.3/25.8/72.2, 
212 | Lubumbashi=-30.8/20.8/70.5, 
213 | Lusaka=-30.4/19.9/68.3, 
214 | Luxembourg City=-44.1/9.3/60.5, 
215 | Lviv=-43.5/7.8/67.9, 
216 | Lyon=-36.1/12.5/59.5, 
217 | Madrid=-35.0/15.0/66.2, 
218 | Mahajanga=-23.7/26.3/74.5, 
219 | Makassar=-21.4/26.7/78.2, 
220 | Makurdi=-22.3/26.0/77.4, 
221 | Malabo=-23.4/26.3/76.6, 
222 | Malé=-20.3/28.0/77.9, 
223 | Managua=-21.3/27.3/76.8, 
224 | Manama=-26.8/26.5/75.2, 
225 | Mandalay=-19.5/28.0/78.3, 
226 | Mango=-19.5/28.1/77.2, 
227 | Manila=-20.5/28.4/79.8, 
228 | Maputo=-27.6/22.8/68.8, 
229 | Marrakesh=-35.1/19.6/69.3, 
230 | Marseille=-33.8/15.8/68.7, 
231 | Maun=-29.5/22.4/74.4, 
232 | Medan=-25.1/26.5/77.4, 
233 | Mek'ele=-26.8/22.7/73.9, 
234 | Melbourne=-36.4/15.1/63.3, 
235 | Memphis=-33.2/17.2/64.6, 
236 | Mexicali=-30.3/23.1/74.2, 
237 | Mexico City=-33.8/17.5/67.5, 
238 | Miami=-22.7/24.9/71.8, 
239 | Milan=-35.7/13.0/61.3, 
240 | Milwaukee=-41.7/8.9/59.8, 
241 | Minneapolis=-41.2/7.8/58.1, 
242 | Minsk=-42.4/6.7/64.3, 
243 | Mogadishu=-27.5/27.1/76.1, 
244 | Mombasa=-21.2/26.3/73.1, 
245 | Monaco=-35.4/16.4/72.4, 
246 | Moncton=-44.8/6.1/58.6, 
247 | Monterrey=-30.2/22.3/72.6, 
248 | Montreal=-46.4/6.8/61.0, 
249 | Moscow=-47.7/5.8/55.1, 
250 | Mumbai=-21.7/27.1/76.2, 
251 | Murmansk=-47.5/0.6/49.2, 
252 | Muscat=-20.1/28.0/77.9, 
253 | Mzuzu=-34.0/17.7/69.1, 
254 | N'Djamena=-20.1/28.3/80.0, 
255 | Naha=-24.2/23.1/72.6, 
256 | Nairobi=-29.7/17.8/67.7, 
257 | Nakhon Ratchasima=-23.6/27.3/78.2, 
258 | Napier=-35.7/14.6/63.8, 
259 | Napoli=-36.5/15.9/67.6, 
260 | Nashville=-33.1/15.4/64.3, 
261 | Nassau=-23.4/24.6/77.8, 
262 | Ndola=-31.0/20.3/69.9, 
263 | New Delhi=-27.2/25.0/77.8, 
264 | New Orleans=-30.8/20.7/69.8, 
265 | New York City=-36.0/12.9/63.3, 
266 | Ngaoundéré=-28.8/22.0/71.1, 
267 | Niamey=-22.0/29.3/78.5, 
268 | Nicosia=-35.0/19.7/69.0, 
269 | Niigata=-37.8/13.9/65.0, 
270 | Nouadhibou=-36.2/21.3/68.7, 
271 | Nouakchott=-24.2/25.7/75.2, 
272 | Novosibirsk=-47.4/1.7/54.6, 
273 | Nuuk=-51.1/-1.4/46.6, 
274 | Odesa=-38.2/10.7/59.6, 
275 | Odienné=-24.9/26.0/76.9, 
276 | Oklahoma City=-33.1/15.9/64.8, 
277 | Omaha=-42.7/10.6/62.9, 
278 | Oranjestad=-21.3/28.1/78.8, 
279 | Oslo=-45.4/5.7/60.2, 
280 | Ottawa=-47.7/6.6/55.8, 
281 | Ouagadougou=-23.1/28.3/80.2, 
282 | Ouahigouya=-21.1/28.6/77.8, 
283 | Ouarzazate=-30.3/18.9/72.3, 
284 | Oulu=-46.8/2.7/52.7, 
285 | Palembang=-20.4/27.3/76.2, 
286 | Palermo=-34.7/18.5/70.1, 
287 | Palm Springs=-26.6/24.5/72.4, 
288 | Palmerston North=-39.9/13.2/61.2, 
289 | Panama City=-20.0/28.0/78.1, 
290 | Parakou=-24.6/26.8/78.2, 
291 | Paris=-38.6/12.3/61.5, 
292 | Perth=-41.6/18.7/65.5, 
293 | Petropavlovsk-Kamchatsky=-48.9/1.9/49.1, 
294 | Philadelphia=-38.0/13.2/65.2, 
295 | Phnom Penh=-21.8/28.3/77.0, 
296 | Phoenix=-26.2/23.9/77.9, 
297 | Pittsburgh=-39.3/10.8/59.4, 
298 | Podgorica=-34.6/15.3/65.2, 
299 | Pointe-Noire=-25.3/26.1/78.5, 
300 | Pontianak=-20.7/27.7/79.6, 
301 | Port Moresby=-22.7/26.9/74.6, 
302 | Port Sudan=-24.1/28.4/76.2, 
303 | Port Vila=-25.8/24.3/75.2, 
304 | Port-Gentil=-24.1/26.0/77.3, 
305 | Portland (OR)=-39.5/12.4/60.7, 
306 | Porto=-35.6/15.7/71.0, 
307 | Prague=-41.6/8.4/57.7, 
308 | Praia=-25.7/24.4/71.8, 
309 | Pretoria=-33.9/18.2/67.6, 
310 | Pyongyang=-39.9/10.8/59.0, 
311 | Rabat=-29.7/17.2/67.5, 
312 | Rangpur=-29.5/24.4/72.5, 
313 | Reggane=-22.1/28.3/80.0, 
314 | Reykjavík=-46.2/4.3/51.4, 
315 | Riga=-41.7/6.2/53.3, 
316 | Riyadh=-34.8/26.0/74.1, 
317 | Rome=-37.0/15.2/69.5, 
318 | Roseau=-28.8/26.2/77.0, 
319 | Rostov-on-Don=-42.8/9.9/62.3, 
320 | Sacramento=-31.9/16.3/64.0, 
321 | Saint Petersburg=-42.7/5.8/55.8, 
322 | Saint-Pierre=-42.7/5.7/56.4, 
323 | Salt Lake City=-37.9/11.6/61.9, 
324 | San Antonio=-26.3/20.8/72.0, 
325 | San Diego=-30.0/17.8/68.1, 
326 | San Francisco=-33.9/14.6/66.8, 
327 | San Jose=-36.2/16.4/67.2, 
328 | San José=-30.0/22.6/69.1, 
329 | San Juan=-20.6/27.2/76.2, 
330 | San Salvador=-25.3/23.1/72.4, 
331 | Sana'a=-32.6/20.0/69.1, 
332 | Santo Domingo=-30.4/25.9/75.1, 
333 | Sapporo=-40.1/8.9/59.2, 
334 | Sarajevo=-44.2/10.1/60.5, 
335 | Saskatoon=-47.4/3.3/53.9, 
336 | Seattle=-35.7/11.3/66.6, 
337 | Seoul=-34.7/12.5/66.5, 
338 | Seville=-29.9/19.2/68.7, 
339 | Shanghai=-32.1/16.7/65.8, 
340 | Singapore=-23.6/27.0/77.4, 
341 | Skopje=-35.6/12.4/60.5, 
342 | Sochi=-35.4/14.2/65.3, 
343 | Sofia=-38.0/10.6/58.2, 
344 | Sokoto=-20.4/28.0/74.8, 
345 | Split=-32.6/16.1/63.5, 
346 | St. John's=-49.0/5.0/53.5, 
347 | St. Louis=-36.1/13.9/63.5, 
348 | Stockholm=-41.9/6.6/54.6, 
349 | Surabaya=-23.9/27.1/76.4, 
350 | Suva=-27.8/25.6/77.7, 
351 | Suwałki=-44.2/7.2/66.7, 
352 | Sydney=-32.6/17.7/69.8, 
353 | Ségou=-26.1/28.0/78.1, 
354 | Tabora=-25.1/23.0/70.4, 
355 | Tabriz=-35.6/12.6/62.1, 
356 | Taipei=-28.9/23.0/78.6, 
357 | Tallinn=-42.7/6.4/61.5, 
358 | Tamale=-20.3/27.9/78.0, 
359 | Tamanrasset=-30.1/21.7/71.4, 
360 | Tampa=-28.1/22.9/75.4, 
361 | Tashkent=-34.2/14.8/64.8, 
362 | Tauranga=-33.6/14.8/65.2, 
363 | Tbilisi=-41.0/12.9/63.3, 
364 | Tegucigalpa=-30.0/21.7/77.2, 
365 | Tehran=-32.2/17.0/66.5, 
366 | Tel Aviv=-29.9/20.0/74.3, 
367 | Thessaloniki=-33.1/16.0/68.8, 
368 | Thiès=-24.9/24.0/76.4, 
369 | Tijuana=-29.2/17.8/65.2, 
370 | Timbuktu=-22.0/28.0/76.4, 
371 | Tirana=-37.5/15.2/67.2, 
372 | Toamasina=-28.0/23.4/71.6, 
373 | Tokyo=-32.1/15.4/65.4, 
374 | Toliara=-27.0/24.1/77.2, 
375 | Toluca=-35.3/12.4/63.1, 
376 | Toronto=-39.8/9.4/58.8, 
377 | Tripoli=-34.6/20.0/69.9, 
378 | Tromsø=-45.1/2.9/52.6, 
379 | Tucson=-29.5/20.9/69.2, 
380 | Tunis=-30.3/18.4/66.9, 
381 | Ulaanbaatar=-49.9/-0.4/49.8, 
382 | Upington=-29.6/20.4/71.5, 
383 | Vaduz=-37.3/10.1/61.2, 
384 | Valencia=-32.4/18.3/66.9, 
385 | Valletta=-32.4/18.8/69.0, 
386 | Vancouver=-40.3/10.4/59.7, 
387 | Veracruz=-24.0/25.4/75.9, 
388 | Vienna=-37.4/10.4/67.2, 
389 | Vientiane=-26.0/25.9/74.0, 
390 | Villahermosa=-22.7/27.1/79.2, 
391 | Vilnius=-43.1/6.0/55.1, 
392 | Virginia Beach=-32.5/15.8/66.7, 
393 | Vladivostok=-41.5/4.9/56.2, 
394 | Warsaw=-43.9/8.5/56.4, 
395 | Washington, 
396 | D.C.=-41.8/14.6/63.5, 
397 | Wau=-18.5/27.8/79.3, 
398 | Wellington=-38.9/12.9/67.2, 
399 | Whitehorse=-48.9/-0.1/50.5, 
400 | Wichita=-36.2/13.9/66.9, 
401 | Willemstad=-20.6/28.0/78.9, 
402 | Winnipeg=-48.6/3.0/52.3, 
403 | Wrocław=-36.2/9.6/62.0, 
404 | Xi'an=-36.6/14.1/61.8, 
405 | Yakutsk=-56.8/-8.8/46.8, 
406 | Yangon=-22.1/27.5/80.4, 
407 | Yaoundé=-25.1/23.8/80.3, 
408 | Yellowknife=-52.5/-4.3/41.5, 
409 | Yerevan=-36.9/12.4/63.5, 
410 | Yinchuan=-42.5/9.0/60.4, 
411 | Zagreb=-38.0/10.7/69.2, 
412 | Zanzibar City=-26.6/26.0/74.5, 
413 | Zürich=-39.7/9.3/57.2, 
414 | Ürümqi=-40.3/7.4/54.8, 
415 | İzmir=-29.2/17.9/68.8}


--------------------------------------------------------------------------------
/src/main/nodejs/Edgar-P-yan/tsconfig.json:
--------------------------------------------------------------------------------
 1 | {
 2 |   "compilerOptions": {
 3 |     "module": "es2022",
 4 |     "target": "es2022",
 5 |     "allowJs": true,
 6 |     "checkJs": true,
 7 |     "outDir": "dist",
 8 |     "types": ["node"]
 9 |   }
10 | }
11 | 


--------------------------------------------------------------------------------
/src/main/nodejs/baseline/.gitignore:
--------------------------------------------------------------------------------
  1 | # Based on https://raw.githubusercontent.com/github/gitignore/main/Node.gitignore
  2 | 
  3 | # Logs
  4 | 
  5 | logs
  6 | _.log
  7 | npm-debug.log_
  8 | yarn-debug.log*
  9 | yarn-error.log*
 10 | lerna-debug.log*
 11 | .pnpm-debug.log*
 12 | 
 13 | # Caches 
 14 | 
 15 | .cache
 16 | 
 17 | # Diagnostic reports (https://nodejs.org/api/report.html)
 18 | 
 19 | report.[0-9]_.[0-9]_.[0-9]_.[0-9]_.json
 20 | 
 21 | # Runtime data
 22 | 
 23 | pids
 24 | _.pid
 25 | _.seed
 26 | *.pid.lock
 27 | 
 28 | # Directory for instrumented libs generated by jscoverage/JSCover
 29 | 
 30 | lib-cov
 31 | 
 32 | # Coverage directory used by tools like istanbul
 33 | 
 34 | coverage
 35 | *.lcov
 36 | 
 37 | # nyc test coverage
 38 | 
 39 | .nyc_output
 40 | 
 41 | # Grunt intermediate storage (https://gruntjs.com/creating-plugins#storing-task-files)
 42 | 
 43 | .grunt
 44 | 
 45 | # Bower dependency directory (https://bower.io/)
 46 | 
 47 | bower_components
 48 | 
 49 | # node-waf configuration
 50 | 
 51 | .lock-wscript
 52 | 
 53 | # Compiled binary addons (https://nodejs.org/api/addons.html)
 54 | 
 55 | build/Release
 56 | 
 57 | # Dependency directories
 58 | 
 59 | node_modules/
 60 | jspm_packages/
 61 | 
 62 | # Snowpack dependency directory (https://snowpack.dev/)
 63 | 
 64 | web_modules/
 65 | 
 66 | # TypeScript cache
 67 | 
 68 | *.tsbuildinfo
 69 | 
 70 | # Optional npm cache directory
 71 | 
 72 | .npm
 73 | 
 74 | # Optional eslint cache
 75 | 
 76 | .eslintcache
 77 | 
 78 | # Optional stylelint cache
 79 | 
 80 | .stylelintcache
 81 | 
 82 | # Microbundle cache
 83 | 
 84 | .rpt2_cache/
 85 | .rts2_cache_cjs/
 86 | .rts2_cache_es/
 87 | .rts2_cache_umd/
 88 | 
 89 | # Optional REPL history
 90 | 
 91 | .node_repl_history
 92 | 
 93 | # Output of 'npm pack'
 94 | 
 95 | *.tgz
 96 | 
 97 | # Yarn Integrity file
 98 | 
 99 | .yarn-integrity
100 | 
101 | # dotenv environment variable files
102 | 
103 | .env
104 | .env.development.local
105 | .env.test.local
106 | .env.production.local
107 | .env.local
108 | 
109 | # parcel-bundler cache (https://parceljs.org/)
110 | 
111 | .parcel-cache
112 | 
113 | # Next.js build output
114 | 
115 | .next
116 | out
117 | 
118 | # Nuxt.js build / generate output
119 | 
120 | .nuxt
121 | dist
122 | 
123 | # Gatsby files
124 | 
125 | # Comment in the public line in if your project uses Gatsby and not Next.js
126 | 
127 | # https://nextjs.org/blog/next-9-1#public-directory-support
128 | 
129 | # public
130 | 
131 | # vuepress build output
132 | 
133 | .vuepress/dist
134 | 
135 | # vuepress v2.x temp and cache directory
136 | 
137 | .temp
138 | 
139 | # Docusaurus cache and generated files
140 | 
141 | .docusaurus
142 | 
143 | # Serverless directories
144 | 
145 | .serverless/
146 | 
147 | # FuseBox cache
148 | 
149 | .fusebox/
150 | 
151 | # DynamoDB Local files
152 | 
153 | .dynamodb/
154 | 
155 | # TernJS port file
156 | 
157 | .tern-port
158 | 
159 | # Stores VSCode versions used for testing VSCode extensions
160 | 
161 | .vscode-test
162 | 
163 | # yarn v2
164 | 
165 | .yarn/cache
166 | .yarn/unplugged
167 | .yarn/build-state.yml
168 | .yarn/install-state.gz
169 | .pnp.*
170 | 
171 | # IntelliJ based IDEs
172 | .idea
173 | 
174 | # Finder (MacOS) folder config
175 | .DS_Store
176 | 


--------------------------------------------------------------------------------
/src/main/nodejs/baseline/index.js:
--------------------------------------------------------------------------------
 1 | import * as readline from 'node:readline';
 2 | import * as fs from 'node:fs';
 3 | 
 4 | const fileName = process.argv[2];
 5 | const stream = fs.createReadStream(fileName);
 6 | const lineStream = readline.createInterface(stream);
 7 | 
 8 | const aggregations = new Map();
 9 | 
10 | for await (const line of lineStream) {
11 |   const [stationName, temperatureStr] = line.split(';');
12 | 
13 |   // use integers for computation to avoid loosing precision
14 |   const temperature = Math.floor(parseFloat(temperatureStr) * 10);
15 | 
16 |   const existing = aggregations.get(stationName);
17 | 
18 |   if (existing) {
19 |     existing.min = Math.min(existing.min, temperature);
20 |     existing.max = Math.max(existing.max, temperature);
21 |     existing.sum += temperature;
22 |     existing.count++;
23 |   } else {
24 |     aggregations.set(stationName, {
25 |       min: temperature,
26 |       max: temperature,
27 |       sum: temperature,
28 |       count: 1,
29 |     });
30 |   }
31 | }
32 | 
33 | printCompiledResults(aggregations);
34 | 
35 | /**
36 |  * @param {Map} aggregations
37 |  *
38 |  * @returns {void}
39 |  */
40 | function printCompiledResults(aggregations) {
41 |   const sortedStations = Array.from(aggregations.keys()).sort();
42 | 
43 |   let result =
44 |     '{' +
45 |     sortedStations
46 |       .map((station) => {
47 |         const data = aggregations.get(station);
48 |         return `${station}=${round(data.min / 10)}/${round(
49 |           data.sum / 10 / data.count
50 |         )}/${round(data.max / 10)}`;
51 |       })
52 |       .join(', ') +
53 |     '}';
54 | 
55 |   console.log(result);
56 | }
57 | 
58 | /**
59 |  * @example
60 |  * round(1.2345) // "1.2"
61 |  * round(1.55) // "1.6"
62 |  * round(1) // "1.0"
63 |  *
64 |  * @param {number} num
65 |  *
66 |  * @returns {string}
67 |  */
68 | function round(num) {
69 |   const fixed = Math.round(10 * num) / 10;
70 | 
71 |   return fixed.toFixed(1);
72 | }
73 | 


--------------------------------------------------------------------------------
/src/main/nodejs/baseline/package-lock.json:
--------------------------------------------------------------------------------
 1 | {
 2 |   "name": "nodejs",
 3 |   "lockfileVersion": 3,
 4 |   "requires": true,
 5 |   "packages": {
 6 |     "": {
 7 |       "devDependencies": {
 8 |         "@types/node": "^20.10.6"
 9 |       }
10 |     },
11 |     "node_modules/@types/node": {
12 |       "version": "20.10.6",
13 |       "resolved": "https://registry.npmjs.org/@types/node/-/node-20.10.6.tgz",
14 |       "integrity": "sha512-Vac8H+NlRNNlAmDfGUP7b5h/KA+AtWIzuXy0E6OyP8f1tCLYAtPvKRRDJjAPqhpCb0t6U2j7/xqAuLEebW2kiw==",
15 |       "dev": true,
16 |       "dependencies": {
17 |         "undici-types": "~5.26.4"
18 |       }
19 |     },
20 |     "node_modules/undici-types": {
21 |       "version": "5.26.5",
22 |       "resolved": "https://registry.npmjs.org/undici-types/-/undici-types-5.26.5.tgz",
23 |       "integrity": "sha512-JlCMO+ehdEIKqlFxk6IfVoAUVmgz7cU7zD/h9XZ0qzeosSHmUJVOzSQvvYSYWXkFXC+IfLKSIffhv0sVZup6pA==",
24 |       "dev": true
25 |     }
26 |   }
27 | }
28 | 


--------------------------------------------------------------------------------
/src/main/nodejs/baseline/package.json:
--------------------------------------------------------------------------------
1 | {
2 |   "type": "module",
3 |   "module": "es2022",
4 |   "devDependencies": {
5 |     "@types/node": "^20.10.6"
6 |   }
7 | }
8 | 


--------------------------------------------------------------------------------
/src/main/nodejs/baseline/tsconfig.json:
--------------------------------------------------------------------------------
 1 | {
 2 |   "compilerOptions": {
 3 |     "module": "es2022",
 4 |     "target": "es2022",
 5 |     "allowJs": true,
 6 |     "checkJs": true,
 7 |     "outDir": "dist",
 8 |     "types": ["node"]
 9 |   }
10 | }
11 | 


--------------------------------------------------------------------------------
/src/main/resources/.dontdelete:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/1brc/nodejs/9975dfbfa32143fb7502e63374a48f9fde1c381d/src/main/resources/.dontdelete


--------------------------------------------------------------------------------
/src/test/resources/.dontdelete:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/1brc/nodejs/9975dfbfa32143fb7502e63374a48f9fde1c381d/src/test/resources/.dontdelete


--------------------------------------------------------------------------------
/src/test/resources/samples/measurements-1.out:
--------------------------------------------------------------------------------
1 | {Kunming=19.8/19.8/19.8}
2 | 


--------------------------------------------------------------------------------
/src/test/resources/samples/measurements-1.txt:
--------------------------------------------------------------------------------
1 | Kunming;19.8
2 | 


--------------------------------------------------------------------------------
/src/test/resources/samples/measurements-10.out:
--------------------------------------------------------------------------------
1 | {Adelaide=15.0/15.0/15.0, Cabo San Lucas=14.9/14.9/14.9, Dodoma=22.2/22.2/22.2, Halifax=12.9/12.9/12.9, Karachi=15.4/15.4/15.4, Pittsburgh=9.7/9.7/9.7, Ségou=25.7/25.7/25.7, Tauranga=38.2/38.2/38.2, Xi'an=24.2/24.2/24.2, Zagreb=12.2/12.2/12.2}
2 | 


--------------------------------------------------------------------------------
/src/test/resources/samples/measurements-10.txt:
--------------------------------------------------------------------------------
 1 | Halifax;12.9
 2 | Zagreb;12.2
 3 | Cabo San Lucas;14.9
 4 | Adelaide;15.0
 5 | Ségou;25.7
 6 | Pittsburgh;9.7
 7 | Karachi;15.4
 8 | Xi'an;24.2
 9 | Dodoma;22.2
10 | Tauranga;38.2
11 | 


--------------------------------------------------------------------------------
/src/test/resources/samples/measurements-2.out:
--------------------------------------------------------------------------------
1 | {Bosaso=19.2/19.2/19.2, Petropavlovsk-Kamchatsky=9.5/9.5/9.5}
2 | 


--------------------------------------------------------------------------------
/src/test/resources/samples/measurements-2.txt:
--------------------------------------------------------------------------------
1 | Bosaso;19.2
2 | Petropavlovsk-Kamchatsky;9.5
3 | 


--------------------------------------------------------------------------------
/src/test/resources/samples/measurements-20.out:
--------------------------------------------------------------------------------
1 | {Abéché1️⃣🐝🏎️=27.3/27.3/27.3, Almaty1️⃣🐝🏎️=15.3/15.3/15.3, Baghdad1️⃣🐝🏎️=26.0/26.0/26.0, Bangkok1️⃣🐝🏎️=25.6/25.6/25.6, Berlin1️⃣🐝🏎️=-0.3/-0.3/-0.3, Birao1️⃣🐝🏎️=33.5/33.5/33.5, Canberra1️⃣🐝🏎️=5.2/5.2/5.2, Chittagong1️⃣🐝🏎️=12.6/12.6/12.6, Da Nang1️⃣🐝🏎️=33.7/33.7/33.7, Edinburgh1️⃣🐝🏎️=19.8/19.8/19.8, Irkutsk1️⃣🐝🏎️=9.9/9.9/9.9, Lhasa1️⃣🐝🏎️=13.4/13.4/13.4, Lyon1️⃣🐝🏎️=1.8/1.8/1.8, Mogadishu1️⃣🐝🏎️=11.5/11.5/11.5, Nashville1️⃣🐝🏎️=-4.9/-4.9/-4.9, Odesa1️⃣🐝🏎️=6.5/6.5/6.5, Parakou1️⃣🐝🏎️=36.3/36.3/36.3, Tamanrasset1️⃣🐝🏎️=17.9/17.9/17.9, Tirana1️⃣🐝🏎️=27.7/27.7/27.7, Xi'an1️⃣🐝🏎️=17.5/17.5/17.5}
2 | 


--------------------------------------------------------------------------------
/src/test/resources/samples/measurements-20.txt:
--------------------------------------------------------------------------------
 1 | Odesa1️⃣🐝🏎️;6.5
 2 | Canberra1️⃣🐝🏎️;5.2
 3 | Lhasa1️⃣🐝🏎️;13.4
 4 | Edinburgh1️⃣🐝🏎️;19.8
 5 | Da Nang1️⃣🐝🏎️;33.7
 6 | Xi'an1️⃣🐝🏎️;17.5
 7 | Berlin1️⃣🐝🏎️;-0.3
 8 | Tamanrasset1️⃣🐝🏎️;17.9
 9 | Abéché1️⃣🐝🏎️;27.3
10 | Baghdad1️⃣🐝🏎️;26.0
11 | Lyon1️⃣🐝🏎️;1.8
12 | Mogadishu1️⃣🐝🏎️;11.5
13 | Bangkok1️⃣🐝🏎️;25.6
14 | Irkutsk1️⃣🐝🏎️;9.9
15 | Parakou1️⃣🐝🏎️;36.3
16 | Almaty1️⃣🐝🏎️;15.3
17 | Birao1️⃣🐝🏎️;33.5
18 | Chittagong1️⃣🐝🏎️;12.6
19 | Tirana1️⃣🐝🏎️;27.7
20 | Nashville1️⃣🐝🏎️;-4.9
21 | 


--------------------------------------------------------------------------------
/src/test/resources/samples/measurements-3.out:
--------------------------------------------------------------------------------
1 | {Bosaso=-15.0/1.3/20.0, Petropavlovsk-Kamchatsky=-9.5/0.0/9.5}
2 | 


--------------------------------------------------------------------------------
/src/test/resources/samples/measurements-3.txt:
--------------------------------------------------------------------------------
1 | Bosaso;5.0
2 | Bosaso;20.0
3 | Bosaso;-5.0
4 | Bosaso;-15.0
5 | Petropavlovsk-Kamchatsky;9.5
6 | Petropavlovsk-Kamchatsky;-9.5
7 | 


--------------------------------------------------------------------------------
/src/test/resources/samples/measurements-boundaries.out:
--------------------------------------------------------------------------------
1 | {Bosaso=-99.9/-99.9/-99.9, Petropavlovsk-Kamchatsky=99.9/99.9/99.9}
2 | 


--------------------------------------------------------------------------------
/src/test/resources/samples/measurements-boundaries.txt:
--------------------------------------------------------------------------------
1 | Bosaso;-99.9
2 | Petropavlovsk-Kamchatsky;99.9
3 | 


--------------------------------------------------------------------------------
/src/test/resources/samples/measurements-complex-utf8.out:
--------------------------------------------------------------------------------
1 | {B=8.9/8.9/8.9, C=38.9/38.9/38.9, CabindaKermānZunhuaRochesterValenzuelaOrūmīyehWugangShuangqiaoTshikapa=3.0/3.0/3.0, ChesterLobnyaSan LeandroHemeiSolweziGrand BourgKaliboS=23.4/23.4/23.4, MirnaPehčevoRopažiGus=16.7/16.7/16.7, PototanSahuayo de MorelosBambergMosigkauFrancisco BeltrãoJelenia GóraTelêmaco Borb=17.5/17.5/17.5, TanjungpinangKasselHaldiaLuxorLạng SơnAt TājīTaraka=10.6/10.6/10.6, aniCartagoEṭ ṬīraTemerinCormeilles-en-ParisisZawyat ech CheïkhS=25.4/25.4/25.4, burgazAl ḨawīyahSalamancaMbanza KongoNchelengeZhangaözenTurbatMatiMangghystaūMalak=21.5/21.5/21.5, cotánSan Ramón de la Nueva OránWausauGbaweTailaiRochester HillsVilla ElisaToba TekS=11.2/11.2/11.2, eLafayetteAsh Shaţ=14.2/14.2/14.2, en IslandKota BharuCiudad López MateosCelayaVinhDuyunLos Mochis‘AjmānNyalaLarkanaWichitaNishi=11.9/11.9/11.9, epé=28.2/28.2/28.2, hanVarkkallaiPort LokoD=10.9/10.9/10.9, iCoahuitlánRabatJahāngīrpur SālkhaniCamUniversity of California-Santa BarbaraSerravalleTelkathuM=13.4/13.4/13.4, igButeboJuršinciKoaniImdinaNova VasDestrnikVarvarinSkomunGornji PetrovciRibnicaKon TumŠavnikPoul=22.5/22.5/22.5, igButeboJuršinciKoaniImdinaNova VasDestrnikVarvarinSkopunGornji PetrovciRibnicaKon TumŠavnikPodl=11.5/11.5/11.5, igButeboJuršinciKoaniImdinaNova VasDestrnikVarvarinSkopunGornji PetrovciRibnicaKon TumŠavnikPoul=18.5/18.5/18.5, inhoSökeDordrechtPoáLaloG=13.1/13.1/13.1, iudad Melchor MúzquizQuinhámelDa=40.5/40.5/40.5, ixButeboJuršinciKoaniImdinaNova VasDestrnikVarvarinSkomunGornji PetrovciRibnicaKon TumŠavnikPoul=0.1/0.1/0.1, l ‘=14.6/14.6/14.6, lhuleuTacurongNavapolatskPiscoDera Ismail KhanLabéAltamiraCavite CityYevpatoriiaTait=22.8/22.8/22.8, liLoretoPlacentiaAliso ViejoChomaPen-y-Bont ar OgwrCojutepeque=12.4/12.4/12.4, lioúpoliBarahonaHoPhuketLe BardoBuena ParkKayesChampigny-sur-MarneHaskovoChathamBatleyEsteioRe=22.5/22.5/22.5, m el Bo=14.6/14.6/14.6, mazunchaleZrenjaninFouchanaSurtPanč=6.7/6.7/6.7, ngoDübendorfC=11.7/11.7/11.7, nt-A=9.2/9.2/9.2, ntington StationKampong SpeuKakataMoschátoBressoVentspilsSaint-CloudTamboSidi Smai’ilDandenon=14.6/14.6/14.6, oCanagatanHelsinkiJabalpurProvidenceRuchengNizhniy NovgorodAhvāzJeparaShaoyangComayagüe=17.3/17.3/17.3, oGumlāSamā’=14.9/14.9/14.9, os Reyes de SalgadoCinisello BalsamoKashibaH=20.0/20.0/20.0, picuíbaJhang CityTepicJayapuraRio BrancoToyamaFangtingSanandajDelhi CantonmentLinghaiShorāpurToy=13.0/13.0/13.0, raKielSibuYatoParanáSanta ClaraYamagataKatihārBeykozImperat=13.5/13.5/13.5, rhamDera Ghazi KhanMiyazakiBhātpār=21.3/21.3/21.3, rugarhVerāvalAlagoinhasEdremitBandırmaSalavatGandajikaLucapaLeesburgTamaRas Tan=10.9/10.9/10.9, skişeh=12.9/12.9/12.9, venGaopingDunhuaAz Zarqā’SylhetKaihuaCaerdyddJāmnagarFuyuanGayaFlorianópolisC=1.9/1.9/1.9, y-le-MoutierSant’ArpinoPljevljaRo=0.8/0.8/0.8, ça PaulistaDarmstadtZhengdingPindamonhangabaEnschedeGirónUttarpāraHeidelbergK=6.0/6.0/6.0, üSosnowiecTanauanMya=18.4/18.4/18.4, ālSongnimSanto TomasKoiduHoshangābādOpoleNovocheboksarskArarasKhannaPunoKoforiduaAhmadpur E=19.4/19.4/19.4, āng=15.7/15.7/15.7, ġFis=9.6/9.6/9.6, ‘AqabahPembaNowgongQu=12.9/12.9/12.9}
2 | 


--------------------------------------------------------------------------------
/src/test/resources/samples/measurements-complex-utf8.txt:
--------------------------------------------------------------------------------
 1 | aniCartagoEṭ ṬīraTemerinCormeilles-en-ParisisZawyat ech CheïkhS;25.4
 2 | picuíbaJhang CityTepicJayapuraRio BrancoToyamaFangtingSanandajDelhi CantonmentLinghaiShorāpurToy;13.0
 3 | lhuleuTacurongNavapolatskPiscoDera Ismail KhanLabéAltamiraCavite CityYevpatoriiaTait;22.8
 4 | āng;15.7
 5 | hanVarkkallaiPort LokoD;10.9
 6 | eLafayetteAsh Shaţ;14.2
 7 | ‘AqabahPembaNowgongQu;12.9
 8 | inhoSökeDordrechtPoáLaloG;13.1
 9 | skişeh;12.9
10 | rhamDera Ghazi KhanMiyazakiBhātpār;21.3
11 | igButeboJuršinciKoaniImdinaNova VasDestrnikVarvarinSkopunGornji PetrovciRibnicaKon TumŠavnikPodl;11.5
12 | igButeboJuršinciKoaniImdinaNova VasDestrnikVarvarinSkopunGornji PetrovciRibnicaKon TumŠavnikPoul;18.5
13 | igButeboJuršinciKoaniImdinaNova VasDestrnikVarvarinSkomunGornji PetrovciRibnicaKon TumŠavnikPoul;22.5
14 | ixButeboJuršinciKoaniImdinaNova VasDestrnikVarvarinSkomunGornji PetrovciRibnicaKon TumŠavnikPoul;0.1
15 | B;8.9
16 | C;38.9
17 | nt-A;9.2
18 | y-le-MoutierSant’ArpinoPljevljaRo;0.8
19 | oGumlāSamā’;14.9
20 | os Reyes de SalgadoCinisello BalsamoKashibaH;20.0
21 | m el Bo;14.6
22 | mazunchaleZrenjaninFouchanaSurtPanč;6.7
23 | ġFis;9.6
24 | epé;28.2
25 | ālSongnimSanto TomasKoiduHoshangābādOpoleNovocheboksarskArarasKhannaPunoKoforiduaAhmadpur E;19.4
26 | iudad Melchor MúzquizQuinhámelDa;40.5
27 | ChesterLobnyaSan LeandroHemeiSolweziGrand BourgKaliboS;23.4
28 | cotánSan Ramón de la Nueva OránWausauGbaweTailaiRochester HillsVilla ElisaToba TekS;11.2
29 | raKielSibuYatoParanáSanta ClaraYamagataKatihārBeykozImperat;13.5
30 | l ‘;14.6
31 | TanjungpinangKasselHaldiaLuxorLạng SơnAt TājīTaraka;10.6
32 | MirnaPehčevoRopažiGus;16.7
33 | üSosnowiecTanauanMya;18.4
34 | ngoDübendorfC;11.7
35 | liLoretoPlacentiaAliso ViejoChomaPen-y-Bont ar OgwrCojutepeque;12.4
36 | burgazAl ḨawīyahSalamancaMbanza KongoNchelengeZhangaözenTurbatMatiMangghystaūMalak;21.5
37 | iCoahuitlánRabatJahāngīrpur SālkhaniCamUniversity of California-Santa BarbaraSerravalleTelkathuM;13.4
38 | lioúpoliBarahonaHoPhuketLe BardoBuena ParkKayesChampigny-sur-MarneHaskovoChathamBatleyEsteioRe;22.5
39 | PototanSahuayo de MorelosBambergMosigkauFrancisco BeltrãoJelenia GóraTelêmaco Borb;17.5
40 | CabindaKermānZunhuaRochesterValenzuelaOrūmīyehWugangShuangqiaoTshikapa;3.0
41 | venGaopingDunhuaAz Zarqā’SylhetKaihuaCaerdyddJāmnagarFuyuanGayaFlorianópolisC;1.9
42 | ntington StationKampong SpeuKakataMoschátoBressoVentspilsSaint-CloudTamboSidi Smai’ilDandenon;14.6
43 | rugarhVerāvalAlagoinhasEdremitBandırmaSalavatGandajikaLucapaLeesburgTamaRas Tan;10.9
44 | oCanagatanHelsinkiJabalpurProvidenceRuchengNizhniy NovgorodAhvāzJeparaShaoyangComayagüe;17.3
45 | ça PaulistaDarmstadtZhengdingPindamonhangabaEnschedeGirónUttarpāraHeidelbergK;6.0
46 | en IslandKota BharuCiudad López MateosCelayaVinhDuyunLos Mochis‘AjmānNyalaLarkanaWichitaNishi;11.9
47 | 


--------------------------------------------------------------------------------
/test.sh:
--------------------------------------------------------------------------------
 1 | #!/bin/bash
 2 | #
 3 | #  Copyright 2023 The original authors
 4 | #
 5 | #  Licensed under the Apache License, Version 2.0 (the "License");
 6 | #  you may not use this file except in compliance with the License.
 7 | #  You may obtain a copy of the License at
 8 | #
 9 | #      http://www.apache.org/licenses/LICENSE-2.0
10 | #
11 | #  Unless required by applicable law or agreed to in writing, software
12 | #  distributed under the License is distributed on an "AS IS" BASIS,
13 | #  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
14 | #  See the License for the specific language governing permissions and
15 | #  limitations under the License.
16 | #
17 | 
18 | set -euo pipefail
19 | 
20 | if [ -z "$1" ]; then
21 |   echo "Usage: test.sh <fork name>"
22 |   exit 1
23 | fi
24 | 
25 | for sample in $(ls src/test/resources/samples/*.txt); do
26 |   echo "Validating calculate_average_$1.sh -- $sample"
27 | 
28 |   rm -f measurements.txt
29 |   ln -s $sample measurements.txt
30 | 
31 |   diff <("./calculate_average_$1.sh") ${sample%.txt}.out
32 | done
33 | rm measurements.txt
34 | 


--------------------------------------------------------------------------------
/test_all.sh:
--------------------------------------------------------------------------------
 1 | #!/bin/bash
 2 | #
 3 | #  Copyright 2023 The original authors
 4 | #
 5 | #  Licensed under the Apache License, Version 2.0 (the "License");
 6 | #  you may not use this file except in compliance with the License.
 7 | #  You may obtain a copy of the License at
 8 | #
 9 | #      http://www.apache.org/licenses/LICENSE-2.0
10 | #
11 | #  Unless required by applicable law or agreed to in writing, software
12 | #  distributed under the License is distributed on an "AS IS" BASIS,
13 | #  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
14 | #  See the License for the specific language governing permissions and
15 | #  limitations under the License.
16 | #
17 | 
18 | set -euo pipefail
19 | 
20 | for impl in $(ls calculate_average_*.sh | sort); do
21 |   noext="${impl%%.sh}"
22 |   name=${noext##calculate_average_}
23 | 
24 |   if output=$(./test.sh "$name" 2>&1); then
25 |     echo "PASS $name"
26 |   else
27 |     echo "FAIL $name"
28 |     echo "$output" 1>&2
29 |   fi
30 | done
31 | 


--------------------------------------------------------------------------------
/tocsv.sh:
--------------------------------------------------------------------------------
 1 | #!/bin/sh
 2 | #
 3 | #  Copyright 2023 The original authors
 4 | #
 5 | #  Licensed under the Apache License, Version 2.0 (the "License");
 6 | #  you may not use this file except in compliance with the License.
 7 | #  You may obtain a copy of the License at
 8 | #
 9 | #      http://www.apache.org/licenses/LICENSE-2.0
10 | #
11 | #  Unless required by applicable law or agreed to in writing, software
12 | #  distributed under the License is distributed on an "AS IS" BASIS,
13 | #  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
14 | #  See the License for the specific language governing permissions and
15 | #  limitations under the License.
16 | #
17 | 
18 | exec sed '
19 | #
20 | # Transform calculate_average*.sh output into semicolon-separated values, one per line.
21 | #
22 | 
23 | # 1. remove "{" and "}"
24 | s/[{}]//g;
25 | 
26 | # 2. replace "=" and "/" with semicolon
27 | s/[=/]/;/g;
28 | 
29 | # 3. id may contain comma, e.g. "Washington, D.C.;-15.1;14.8;44.8, Wau;-2.1;27.4;53.4"
30 | # so replace ", " with a newline only if it is preceded by a digit
31 | s/\([0-9]\), /\1\n/g
32 | '
33 | 


--------------------------------------------------------------------------------