├── serbia
    ├── .gitignore
    ├── requirements.txt
    ├── README.md
    ├── daily-measurement.sh
    └── serbia2input.py
├── .gitignore
├── requirements.txt
├── shp2osm.sh
├── processing_state.py
├── inputcsv2shp.py
├── refresh-osm-data.sh
├── config.yml
├── extras
    ├── add_level9_id_to_osm.py
    ├── add_level8_id_to_osm.py
    └── add_subarea_settlements.py
├── atomic_write.py
├── send_notification.py
├── common.py
├── measure_quality.py
├── conflate-report.py
├── templates
    └── index_template.html
├── README.md
├── translation.py
├── conflate.py
└── LICENSE


/serbia/.gitignore:
--------------------------------------------------------------------------------
1 | rgz-password


--------------------------------------------------------------------------------
/.gitignore:
--------------------------------------------------------------------------------
 1 | __pycache__/
 2 | .idea/
 3 | input/
 4 | output/
 5 | osm-password
 6 | rpj.osm
 7 | progress.csv
 8 | izlaz.csv
 9 | conflate-progress.pickle
10 | process.log
11 | measurement.log
12 | overpass_db/
13 | ogr2osm/
14 | 


--------------------------------------------------------------------------------
/requirements.txt:
--------------------------------------------------------------------------------
 1 | Fiona==1.8.20
 2 | Shapely==1.8.0
 3 | overpy==0.4
 4 | pyproj==2.6.1.post1
 5 | osmapi==1.3.0
 6 | matplotlib==3.5.1
 7 | Jinja2==3.0.1
 8 | requests~=2.25.1
 9 | beautifulsoup4~=4.10.0
10 | lxml==4.8.0
11 | PyYAML==6.0
12 | 


--------------------------------------------------------------------------------
/serbia/requirements.txt:
--------------------------------------------------------------------------------
 1 | Fiona==1.8.20
 2 | Shapely==1.8.0
 3 | overpy==0.4
 4 | pyproj==2.6.1.post1
 5 | osmapi==1.3.0
 6 | matplotlib==3.5.1
 7 | Jinja2==3.0.1
 8 | requests~=2.25.1
 9 | beautifulsoup4~=4.10.0
10 | lxml==4.8.0
11 | ogr2osm==1.1.1


--------------------------------------------------------------------------------
/shp2osm.sh:
--------------------------------------------------------------------------------
 1 | #!/bin/bash
 2 | 
 3 | set -euo pipefail
 4 | 
 5 | 
 6 | if [[ $# -ne 2 ]]; then
 7 |     echo 'Too many/few arguments, expecting two, call it with: ./shp2osm.sh <input-shp> <output-osm>' >&2
 8 |     exit 1
 9 | fi
10 | 
11 | inputShp=$1
12 | outputOsm=$2
13 | 
14 | echo "Converting input shp '$1' to output OSM '$2'"
15 | 
16 | if [[ ! -d "ogr2osm/" ]]
17 | then
18 |     # TODO: switch to new ogr2osm version
19 |     echo "ogr2osm does not exists, will git clone it now"
20 |     git clone https://github.com/pnorman/ogr2osm.git
21 | fi
22 | 
23 | python3 ogr2osm/ogr2osm.py -t translation.py -f --split-ways=1 -o $outputOsm $inputShp
24 | 


--------------------------------------------------------------------------------
/processing_state.py:
--------------------------------------------------------------------------------
 1 | from enum import Enum
 2 | 
 3 | 
 4 | class ProcessingState(Enum):
 5 |     """
 6 |     Potential results of conflation
 7 |     """
 8 |     NO = 1
 9 |     CHECKED_POSSIBLE = 2
10 |     CONFLATED = 3
11 |     ERROR_END_POINTS_FAR_APART = 4
12 |     ERROR_GEOMETRY_WRONG = 5
13 |     ERROR_SHARED_WAY_NOT_FOUND = 6
14 |     ERROR_WAY_NOT_FOUND = 7
15 |     ERROR_MULTIPLE_SHARED_WAYS = 8
16 |     ERROR_MULTIPLE_SINGLE_WAY = 9
17 |     ERROR_NODES_WITH_TAGS = 10
18 |     ERROR_NATIONAL_BORDER = 11
19 |     ERROR_UNEXPECTED_TAG = 12
20 |     ERROR_NODE_IN_OTHER_WAYS = 13
21 |     ERROR_NODE_IN_NATIONAL_BORDER = 14
22 |     ERROR_NODE_IN_OTHER_RELATION = 15
23 |     ERROR_NODE_IN_NATIONAL_RELATION = 16
24 |     ERROR_INVALID_SHAPE = 17
25 |     ERROR_CLOSED_SHAPE = 18
26 |     ERROR_OVERLAPPING_WAYS = 19
27 |     ERROR_TOO_MANY_NODES = 20


--------------------------------------------------------------------------------
/serbia/README.md:
--------------------------------------------------------------------------------
 1 | This folder contains set of scripts to aid daily checks of OSM admin boundaries in Serbia against official cadastre data.
 2 | All scripts here are very much specific to Serbia and not of interest for other readers.
 3 | But do check how it all works end to end.
 4 | 
 5 | All of this is done by using local overpass server and doing couple of steps:
 6 | * Initialize data from yesterday (PBF data) to serve as a baseline and calculate statistics
 7 | * Update cadastre data from today and calculate statistics again, finding differences that are due to cadastre changes
 8 | * Update today's OSM data and calculate statistics again, finding differences that are due to OSM changes
 9 | 
10 | If there are any changes (either cadastre or OSM) that are worse than yesterday, shoot Telegram message.
11 | 
12 | Start with `daily-measurement.sh` script to dive in.


--------------------------------------------------------------------------------
/inputcsv2shp.py:
--------------------------------------------------------------------------------
 1 | import csv
 2 | import sys
 3 | 
 4 | import fiona
 5 | from fiona.crs import from_epsg
 6 | from shapely.geometry import mapping
 7 | from shapely.wkt import loads
 8 | 
 9 | from common import load_level9_features
10 | 
11 | csv.field_size_limit(sys.maxsize)
12 | 
13 | schema = {
14 |     'geometry': ['Polygon', 'MultiPolygon'],
15 |     'properties': {
16 |         'level9id': 'str',
17 |         'level9name': 'str',
18 |         'level8id': 'str',
19 |         'level8name': 'str',
20 |         'level7id': 'str',
21 |         'level7name': 'str',
22 |         'level6id': 'str',
23 |         'level6name': 'str'
24 |     }
25 | }
26 | 
27 | 
28 | def main(input_csv_file: str, output_shp_file: str):
29 |     print(f'Loading level9 data from {input_csv_file}')
30 |     level9_features = load_level9_features(input_csv_file)
31 | 
32 |     print(f'Writing level9 data to {output_shp_file}')
33 |     with fiona.collection(output_shp_file, "w", "ESRI Shapefile", schema, crs=from_epsg(4326), encoding='utf-8') as output:
34 |         for level9_feature in level9_features:
35 |             geometry = loads(level9_feature['wkt'])
36 |             output.write({
37 |                 'properties': {
38 |                     'level9id': level9_feature['level9_id'],
39 |                     'level9name': level9_feature['level9_name'],
40 |                     'level8id': level9_feature['level8_id'],
41 |                     'level8name': level9_feature['level8_name'],
42 |                     'level7id': level9_feature['level7_id'],
43 |                     'level7name': level9_feature['level7_name'],
44 |                     'level6id': level9_feature['level6_id'],
45 |                     'level6name': level9_feature['level6_name']
46 |                 },
47 |                 'geometry': mapping(geometry)})
48 |     print('Done')
49 | 
50 | 
51 | if __name__ == '__main__':
52 |     if len(sys.argv) != 3:
53 |         print("Usage: ./inputcsv2shp.py <input_csv_file> <output_shp_file>")
54 |         exit()
55 |     input_csv_file = sys.argv[1]
56 |     output_shp_file = sys.argv[2]
57 |     main(input_csv_file, output_shp_file)
58 | 


--------------------------------------------------------------------------------
/refresh-osm-data.sh:
--------------------------------------------------------------------------------
 1 | #!/bin/bash
 2 | 
 3 | set -euo pipefail
 4 | 
 5 | # This script downloads and restarts/refresh overpass server with map of some country. It takes around 10 minutes for Serbia, YMMV.
 6 | 
 7 | # Details how to install here: https://wiki.openstreetmap.org/wiki/Overpass_API/Installation
 8 | # or here: http://overpass-api.de/no_frills.html
 9 | # Copy this in overpass server directory
10 | # Create ./build directory inside overpass server directory where you will build it
11 | # Change ./build/bin/rules_loop.sh such that it doesn't do infinite loop, but does areas only once
12 | 
13 | if [[ $# -ne 4 ]]; then
14 |     echo 'Too many/few arguments, expecting two, call it with: ./refresh-osm-data.sh <continent> <country> <today|yesterday> <overpass_db_dir>' >&2
15 |     exit 1
16 | fi
17 | 
18 | continent=$1
19 | region=$2
20 | rel_overpass_db=$4
21 | 
22 | if [ $3 = "yesterday" ]; then
23 |   yesterday=`date -d 'now - 2day' +%y%m%d` # Two days as geofabrik releases data in early morning UTC time
24 |   url="http://download.geofabrik.de/$continent/$region-$yesterday.osm.pbf"
25 | else
26 |   url="http://download.geofabrik.de/$continent/$region-latest.osm.pbf"
27 | fi
28 | 
29 | echo "Using URL $url"
30 | 
31 | if [ ! -z "`docker ps | grep overpass_$region`" ]; then
32 |   docker stop overpass_$region
33 | fi
34 | if [ ! -z "`docker ps -a | grep overpass_$region`" ]; then
35 |   docker rm overpass_$region
36 | fi
37 | 
38 | absolute_overpass_dir=`realpath $rel_overpass_db`
39 | echo "Absolute path to overpass dir: $absolute_overpass_dir"
40 | rm -rf $absolute_overpass_dir/*
41 | 
42 | docker run \
43 |   -e OVERPASS_META=yes \
44 |   -e OVERPASS_MODE=init \
45 |   -e OVERPASS_PLANET_URL=$url \
46 |   -e OVERPASS_RULES_LOAD=10 \
47 |   -e OVERPASS_PLANET_PREPROCESS='mv /db/planet.osm.bz2 /db/planet.osm.pbf && osmium cat -o /db/planet.osm.bz2 /db/planet.osm.pbf && rm /db/planet.osm.pbf' \
48 |   -v $absolute_overpass_dir/:/db \
49 |   -p 12345:80 \
50 |   -i \
51 |   --name overpass_$region wiktorn/overpass-api
52 | 
53 | docker start overpass_$region
54 | 
55 | echo "Waiting for container to boot up"
56 | until [ "`docker inspect -f {{.State.Health.Status}} overpass_$region`" == "healthy" ]; do
57 |     date
58 |     echo "Still waiting for container to boot up"
59 |     sleep 5
60 | done;
61 | 
62 | sleep 10
63 | 


--------------------------------------------------------------------------------
/config.yml:
--------------------------------------------------------------------------------
 1 | # Official name of country. Needed for various Overpass OSM queries
 2 | country: Србија
 3 | 
 4 | # Used as a template for "source" tag of changesets
 5 | changeset_source: "open Serbian cadastre data Jan 2022"
 6 | 
 7 | # Used as a comment for changesets when doing semi-automatic conflation
 8 | changeset_comment: "Serbian bot - conflating boundaries (https://lists.openstreetmap.org/pipermail/imports/2020-January/006149.html)."
 9 | 
10 | # Name of the OSM tag that keeps ID of your level 9 entities (settlements...). It can be as simple as "ref"
11 | level9_ref_key: "ref:RS:naselje"
12 | 
13 | # Name of the OSM tag that keeps ID of your level 8 entities (municipalities...). It can be as simple as "ref"
14 | level8_ref_key: "ref:RS:opstina"
15 | 
16 | # Overpass endpoint. You need to have docker to set up your own Overpass instance (see "refresh-osm-data.sh" for details)
17 | # Commented out are other potential options, but beware of throttling and misuse
18 | overpass_url: "http://localhost:12345/api/interpreter"
19 | # overpass_url: "https://lz4.overpass-api.de/api/interpreter"
20 | # overpass_url: "http://overpass-api.de/api/interpreter"
21 | 
22 | # If True, scripts will just assess conflation potential and will not submit anything to OSM.
23 | # If False, there will be actual process of OSM submission. In that case, please set "auto_proceed" to false, so you
24 | # can control process after each way.
25 | dry_run: True
26 | 
27 | # Should human control stepping up after each processed way. Set to true when actually submitting to OSM.
28 | auto_proceed: True
29 | 
30 | # If way is eligible for conflation, and some other nodes/ways relations are glued to it, should we unglue them.
31 | # If you unglue them, you will get two ways with same geometries (with different tags, of course). If you set this to False,
32 | # ways will be reported as not eligible for conflation.
33 | unglue_ways_as_needed: True
34 | 
35 | # How far apart any endpoints of the way should be from OSM way to consider them eligable for conflation.
36 | # If any endpoint is in greater distance than this, script will not conflate this road. If you set this too low,
37 | # lot of ways that could be conflated will be reported as not possible. If you set this too high, you might get false
38 | # positives and wrong ways could be conflated by error.
39 | max_distance_end_points_to_consider_in_meters: 500
40 | 


--------------------------------------------------------------------------------
/serbia/daily-measurement.sh:
--------------------------------------------------------------------------------
 1 | #!/bin/bash
 2 | 
 3 | # Main script that can be run daily (in cron) to find differences and report result.
 4 | # Set TELEGRAM_BOT_TOKEN and TELEGRAM_CHAT_ID if you want to get updates over Telegram.
 5 | # You can use it for base for your region.
 6 | 
 7 | set -euo pipefail
 8 | 
 9 | date
10 | 
11 | currentdate=`date +%Y%m%d`
12 | yesterday=`date -d 'now - 1day' +%Y%m%d`
13 | 
14 | echo "Current date is $currentdate, yesterday is $yesterday"
15 | 
16 | # Check if there is overpass set up at all
17 | response=$(curl --write-out "%{http_code}\n" --silent --output /dev/null "http://localhost:12345/api/interpreter?data=%3Cprint%20mode=%22body%22/%3E" || true)
18 | overpass_works=0
19 | if [[ $response == "200" ]]; then
20 |   echo "Overpass works"
21 |   overpass_works=1
22 | else
23 |   echo "Overpass is not working"
24 | fi
25 | 
26 | function refresh_cadastre_data {
27 |   python3 serbia2input.py input/all.csv
28 |   python3 ../inputcsv2shp.py input/all.csv output/shp/all.shp
29 |   ../shp2osm.sh output/shp/all.shp output/osm/all.osm
30 | }
31 | 
32 | if [ ! -f input/all.csv ]; then
33 |   echo "No input file, recreating from scratch (losing diff from Serbia cadastre from yesterday)"
34 |   refresh_cadastre_data
35 | fi
36 | 
37 | shopt -s nullglob
38 | shp_files=( ./output/shp/*.shp )
39 | found_files=( ${#shp_files[@]} )
40 | echo "Found $found_files files"
41 | 
42 | if [[ $found_files -eq "0" ]]; then
43 |   echo "No shp files, recreating them from scratch (losing diff from Serbia cadastre from yesterday)"
44 |   refresh_cadastre_data
45 | fi
46 | 
47 | 
48 | echo "Setting up yesterday data"
49 | ../refresh-osm-data.sh europe serbia yesterday ../overpass_db
50 | 
51 | # Do baseline measurement
52 | python3 ../measure_quality.py input/all.csv output/level9-baseline-$yesterday.csv
53 | sort -o output/level9-baseline-$yesterday.csv output/level9-baseline-$yesterday.csv
54 | 
55 | # Refresh cadastre and do measurements now
56 | echo "Refreshing cadastre data"
57 | refresh_cadastre_data
58 | sleep 10
59 | 
60 | echo "Measuring settlements after cadastre is refreshed"
61 | python3 ../measure_quality.py input/all.csv output/level9-cadastre-$currentdate.csv
62 | sort -o output/level9-cadastre-$currentdate.csv output/level9-cadastre-$currentdate.csv
63 | diff -u output/level9-baseline-$yesterday.csv output/level9-cadastre-$currentdate.csv > output/level9-cadastre-$currentdate.diff || true
64 | python3 send_notification.py cadastre level9 output/level9-baseline-$yesterday.csv output/level9-cadastre-$currentdate.csv
65 | 
66 | # Refresh OSM and do measurements now
67 | echo "Refreshing OSM data"
68 | ./refresh-osm-data.sh europe serbia today
69 | sleep 10
70 | 
71 | echo "Measuring settlements after OSM is refreshed"
72 | python3 ../measure_quality.py input/all.csv output/level9-osm-$currentdate.csv
73 | sort -o output/level9-osm-$currentdate.csv output/level9-osm-$currentdate.csv
74 | diff -u output/level9-baseline-$yesterday.csv output/level9-osm-$currentdate.csv > output/level9-osm-$currentdate.diff || true
75 | python3 send_notification.py osm level9 output/level9-baseline-$yesterday.csv output/level9-osm-$currentdate.csv
76 | cp output/level9-osm-$currentdate.csv output/level9-baseline-$currentdate.csv
77 | 
78 | echo "Measurement done for $currentdate"
79 | sleep 10
80 | 


--------------------------------------------------------------------------------
/extras/add_level9_id_to_osm.py:
--------------------------------------------------------------------------------
 1 | """
 2 | This script semi-automatically adds level9 ids to OSM.
 3 | """
 4 | 
 5 | import os
 6 | import sys
 7 | import time
 8 | import yaml
 9 | 
10 | import osmapi
11 | import overpy
12 | 
13 | current = os.path.dirname(os.path.realpath(__file__))
14 | parent = os.path.dirname(current)
15 | sys.path.append(parent)
16 | 
17 | from common import get_polygon_by_cadastre_id, load_level9_features
18 | 
19 | 
20 | def main(config, overpass_api, input_csv_file):
21 |     level9_features = load_level9_features(input_csv_file)
22 | 
23 |     level9_map = {}  # maps (level8 name, level9 name) -> level9 id
24 |     for level9_feature in level9_features:
25 |         level8_name = level9_feature['level8_name']
26 |         level9_name = level9_feature['level9_name']
27 |         level9_id = level9_feature['level9_id']
28 |         if (level8_name, level9_name) not in level9_map:
29 |             level9_map[(level8_name, level9_name)] = level9_id
30 | 
31 |     api = osmapi.OsmApi(passwordfile='osm-password',
32 |                         changesetauto=True, changesetautosize=20, changesetautotags=
33 |                         {u"comment": f"Bot - adding missing {config['level9_ref_key']}",
34 |                          u"tag": u"mechanical=yes", u"source": config['changeset_source']})
35 | 
36 |     for i, level8_name_level9_name in enumerate(level9_map.keys()):
37 |         level8_name = level8_name_level9_name[0]
38 |         level9_name = level8_name_level9_name[1]
39 |         level9_id = level9_map[level8_name_level9_name]
40 |         overpass_level9_polygon, osm_level9_name, osm_relation_id, national_border = \
41 |             get_polygon_by_cadastre_id(overpass_api, 9, level9_id, country=config['country'], id_key=config['level9_ref_key'])
42 | 
43 |         if overpass_level9_polygon is None:
44 |             print(f'Skipping {level8_name}/{level9_name}')
45 |             continue
46 |         time.sleep(3)
47 |         relation = api.RelationGet(osm_relation_id)
48 |         if relation['tag']['boundary'] != 'administrative' or relation['tag']['type'] != 'boundary':
49 |             print(f'Something fishy with relation {level8_name}/{level9_name}, skipping it:\n {relation["tag"]}')
50 |             continue
51 |         if config['level9_ref_key'] in relation['tag']:
52 |             print(f'Already done {level8_name}/{level9_name}, skipping it')
53 |             continue
54 | 
55 |         for k, v in relation['tag'].items():
56 |             if k == 'metadata':
57 |                 continue
58 |             if k.startswith('tag_') or k.startswith('val_') or k == 'boundary' or k == 'type':
59 |                 continue
60 |             print(f'{k}: {v}')
61 |         print(f'https://www.openstreetmap.org/relation/{relation["id"]}')
62 |         accepted = False
63 |         while True:
64 |             response = input(f'({i}/{len(level9_map)}) Are you sure you want to add {config["level9_ref_key"]} {level9_id} to {level8_name}/{level9_name} (Y/n/c)?')
65 |             if response == '' or response.lower() == 'y':
66 |                 accepted = True
67 |             if response.lower() == u'c':
68 |                 new_answer = input('Again: ')
69 |                 if new_answer == '':
70 |                     continue
71 |                 else:
72 |                     accepted = True
73 |             break
74 |         if not accepted:
75 |             continue
76 |         relation['tag'][config["level9_ref_key"]] = level9_id
77 |         api.RelationUpdate(relation)
78 |     api.flush()
79 | 
80 | 
81 | if __name__ == '__main__':
82 |     with open('config.yml', 'r') as config_yml_file:
83 |         config = yaml.safe_load(config_yml_file)
84 | 
85 |     overpass_api = overpy.Overpass(url=config['overpass_url'])
86 | 
87 |     if len(sys.argv) != 2:
88 |         print("Usage: ./extras/add_level9_id_to_osm.py <input_csv_file>")
89 |         exit()
90 |     input_csv_file = sys.argv[1]
91 |     main(config, overpass_api, input_csv_file)


--------------------------------------------------------------------------------
/extras/add_level8_id_to_osm.py:
--------------------------------------------------------------------------------
 1 | """
 2 | This script semi-automatically adds level8 ids to OSM.
 3 | """
 4 | 
 5 | import os
 6 | import sys
 7 | import time
 8 | 
 9 | import osmapi
10 | import overpy
11 | import yaml
12 | 
13 | current = os.path.dirname(os.path.realpath(__file__))
14 | parent = os.path.dirname(current)
15 | sys.path.append(parent)
16 | 
17 | from common import get_polygon_by_cadastre_id, load_level9_features
18 | 
19 | 
20 | def main(config, overpass_api, input_csv_file):
21 |     level9_features = load_level9_features(input_csv_file)
22 | 
23 |     level8_map = {}  # maps (level6 name, level8 name) -> level8 id
24 |     for level9_feature in level9_features:
25 |         level6_name = level9_feature['level6_name']
26 |         level8_name = level9_feature['level8_name']
27 |         level8_id = level9_feature['level8_id']
28 |         if (level6_name, level8_name) not in level8_map:
29 |             level8_map[(level6_name, level8_name)] = level8_id
30 | 
31 |     api = osmapi.OsmApi(passwordfile='osm-password',
32 |                         changesetauto=True, changesetautosize=20, changesetautotags=
33 |                         {u"comment": u"Serbian lint bot - adding missing {}".format(config['level8_ref_key']),
34 |                          u"tag": u"mechanical=yes", u"source": config['changeset_source']})
35 |     for i, level6_name_level8_name in enumerate(level8_map.keys()):
36 |         level6_name = level6_name_level8_name[0]
37 |         level8_name = level6_name_level8_name[1]
38 |         level8_id = level8_map[level6_name_level8_name]
39 |         overpass_level8_polygon, osm_level8_name, osm_relation_id, national_border = \
40 |             get_polygon_by_cadastre_id(overpass_api, 8, level8_id, country=config['country'], id_key=config['level8_ref_key'])
41 | 
42 |         if overpass_level8_polygon is None:
43 |             print(f'Skipping {level6_name}/{level8_name}')
44 |             continue
45 |         time.sleep(1)
46 |         relation = api.RelationGet(osm_relation_id)
47 |         if relation['tag']['boundary'] != 'administrative' or relation['tag']['type'] != 'boundary':
48 |             print(f'Something fishy with relation {level6_name}/{level8_name}, skipping it:\n {relation["tag"]}')
49 |             continue
50 |         if 'ref:RS:opstina' in relation['tag']:
51 |             print(f'Already done {level6_name}/{level8_name}, skipping it')
52 |             continue
53 | 
54 |         for k, v in relation['tag'].items():
55 |             if k == 'metadata':
56 |                 continue
57 |             if k.startswith('tag_') or k.startswith('val_') or k == 'boundary' or k == 'type':
58 |                 continue
59 |             print(f'{k}: {v}')
60 |         print(f'https://www.openstreetmap.org/relation/{relation["id"]}')
61 |         accepted = False
62 |         while True:
63 |             response = input(f'({i}/{len(level8_map)}) Are you sure you want to add {config["level8_ref_key"]} {level8_id} to {level6_name}/{level8_name} (Y/n/c)?')
64 |             if response == '' or response.lower() == 'y':
65 |                 accepted = True
66 |             if response.lower() == u'c':
67 |                 new_answer = input('Again: ')
68 |                 if new_answer == '':
69 |                     continue
70 |                 else:
71 |                     accepted = True
72 |             break
73 |         if not accepted:
74 |             continue
75 |         relation['tag'][config["level8_ref_key"]] = level8_id
76 |         api.RelationUpdate(relation)
77 |     api.flush()
78 | 
79 | 
80 | if __name__ == '__main__':
81 |     with open('config.yml', 'r') as config_yml_file:
82 |         config = yaml.safe_load(config_yml_file)
83 | 
84 |     overpass_api = overpy.Overpass(url=config['overpass_url'])
85 | 
86 |     if len(sys.argv) != 2:
87 |         print("Usage: ./extras/add_level8_id_to_osm.py <input_csv_file>")
88 |         exit()
89 |     input_csv_file = sys.argv[1]
90 |     main(config, overpass_api, input_csv_file)
91 | 


--------------------------------------------------------------------------------
/atomic_write.py:
--------------------------------------------------------------------------------
 1 | """
 2 | Kindly borrowed from https://code.activestate.com/recipes/579097-safely-and-atomically-write-to-a-file/
 3 | """
 4 | 
 5 | import contextlib
 6 | import os
 7 | import stat
 8 | import sys
 9 | import tempfile
10 | 
11 | 
12 | @contextlib.contextmanager
13 | def atomic_write(filename, text=True, keep=True,
14 |                  owner=None, group=None, perms=None,
15 |                  suffix='.bak', prefix='tmp'):
16 |     """Context manager for overwriting a file atomically.
17 | 
18 |     Usage:
19 | 
20 |     >>> with atomic_write("myfile.txt") as f:  # doctest: +SKIP
21 |     ...     f.write("data")
22 | 
23 |     The context manager opens a temporary file for writing in the same
24 |     directory as `filename`. On cleanly exiting the with-block, the temp
25 |     file is renamed to the given filename. If the original file already
26 |     exists, it will be overwritten and any existing contents replaced.
27 | 
28 |     (On POSIX systems, the rename is atomic. Other operating systems may
29 |     not support atomic renames, in which case the function name is
30 |     misleading.)
31 | 
32 |     If an uncaught exception occurs inside the with-block, the original
33 |     file is left untouched. By default the temporary file is also
34 |     preserved, for diagnosis or data recovery. To delete the temp file,
35 |     pass `keep=False`. Any errors in deleting the temp file are ignored.
36 | 
37 |     By default, the temp file is opened in text mode. To use binary mode,
38 |     pass `text=False` as an argument. On some operating systems, this make
39 |     no difference.
40 | 
41 |     The temporary file is readable and writable only by the creating user.
42 |     By default, the original ownership and access permissions of `filename`
43 |     are restored after a successful rename. If `owner`, `group` or `perms`
44 |     are specified and are not None, the file owner, group or permissions
45 |     are set to the given numeric value(s). If they are not specified, or
46 |     are None, the appropriate value is taken from the original file (which
47 |     must exist).
48 | 
49 |     By default, the temp file will have a name starting with "tmp" and
50 |     ending with ".bak". You can vary that by passing strings as the
51 |     `suffix` and `prefix` arguments.
52 |     """
53 |     t = (uid, gid, mod) = (owner, group, perms)
54 |     if any(x is None for x in t):
55 |         info = os.stat(filename)
56 |         if uid is None:
57 |             uid = info.st_uid
58 |         if gid is None:
59 |             gid = info.st_gid
60 |         if mod is None:
61 |             mod = stat.S_IMODE(info.st_mode)
62 |     path = os.path.dirname(filename)
63 |     fd, tmp = tempfile.mkstemp(suffix=suffix, prefix=prefix, dir=path, text=text)
64 |     try:
65 |         replace = os.replace  # Python 3.3 and better.
66 |     except AttributeError:
67 |         if sys.platform == 'win32':
68 |             # FIXME This is definitely not atomic!
69 |             # But it's how (for example) Mercurial does it, as of 2016-03-23
70 |             # https://selenic.com/repo/hg/file/tip/mercurial/windows.py
71 |             def replace(source, dest):
72 |                 assert sys.platform == 'win32'
73 |                 try:
74 |                     os.rename(source, dest)
75 |                 except OSError as err:
76 |                     if err.winerr != 183:
77 |                         raise
78 |                     os.remove(dest)
79 |                     os.rename(source, dest)
80 |         else:
81 |             # Atomic on POSIX. Not sure about Cygwin, OS/2 or others.
82 |             replace = os.rename
83 |     try:
84 |         with os.fdopen(fd, 'w' if text else 'wb') as f:
85 |             yield f
86 |         # Perform an atomic rename (if possible). This will be atomic on
87 |         # POSIX systems, and Windows for Python 3.3 or higher.
88 |         replace(tmp, filename)
89 |         tmp = None
90 |         os.chown(filename, uid, gid)
91 |         os.chmod(filename, mod)
92 |     finally:
93 |         if (tmp is not None) and (not keep):
94 |             # Silently delete the temporary file. Ignore any errors.
95 |             try:
96 |                 os.unlink(tmp)
97 |             except:
98 |                 pass


--------------------------------------------------------------------------------
/send_notification.py:
--------------------------------------------------------------------------------
  1 | import csv
  2 | import datetime
  3 | import os
  4 | import sys
  5 | import time
  6 | 
  7 | import requests
  8 | 
  9 | 
 10 | def telegram_sendtext(bot_message: str):
 11 |     bot_token = os.environ['TELEGRAM_BOT_TOKEN']
 12 |     bot_chat_id = os.environ['TELEGRAM_CHAT_ID']
 13 |     send_text = 'https://api.telegram.org/bot' + bot_token + '/sendMessage?chat_id=' + bot_chat_id + '&parse_mode=Markdown&text=' + bot_message
 14 |     response = requests.get(send_text)
 15 |     time.sleep(3)
 16 |     return response.json()
 17 | 
 18 | 
 19 | def process(diff_type: str, entity_type: str, baseline_csv: str, new_csv: str) -> int:
 20 |     # Load saved state
 21 |     baseline_entities = {}
 22 |     with open(baseline_csv) as csvfile:
 23 |         reader = csv.DictReader(csvfile)
 24 |         for row in reader:
 25 |             baseline_entities[row['relation_id']] = {
 26 |                 'district': row['level6'],
 27 |                 'name': row['level8'] if entity_type == 'level8' else row['level9'],
 28 |                 'relation_id': row['relation_id'], 'area_not_shared': float(row['area_not_shared'])
 29 |             }
 30 |     new_entities = {}
 31 |     with open(new_csv) as csvfile:
 32 |         reader = csv.DictReader(csvfile)
 33 |         for row in reader:
 34 |             new_entities[row['relation_id']] = {
 35 |                 'level6': row['level6'],
 36 |                 'name': row['level8'] if entity_type == 'level8' else row['level9'],
 37 |                 'area_not_shared': float(row['area_not_shared'])
 38 |             }
 39 | 
 40 |     messages_sent = 0
 41 |     for new_relation_id, new_entity in new_entities.items():
 42 |         if messages_sent > 10:
 43 |             telegram_sendtext('{0} refreshed and compared with {1}, but there are more than 10 regressions, stopping with sending'.format(
 44 |                 diff_type, entity_type
 45 |             ))
 46 |             break
 47 |         if new_relation_id not in baseline_entities:
 48 |             telegram_sendtext('{0} refreshed. Relation {1} ({2} {3}) exist now and it didn\'t existed before.'.format(
 49 |                 diff_type, new_relation_id, entity_type, new_entity['name']
 50 |             ))
 51 |             messages_sent += 1
 52 |             continue
 53 |         baseline_area_not_shared = baseline_entities[new_relation_id]['area_not_shared']
 54 |         new_area_not_shared = new_entity['area_not_shared']
 55 |         if new_area_not_shared > 0 and (new_area_not_shared - baseline_area_not_shared) > 0:  # It was: new_area_not_shared > 0.01
 56 |             telegram_sendtext('{0} refreshed and {1} {2} (district {3}, relation {4}) was different {5}%, but now it is {6}%'.format(
 57 |                 diff_type, entity_type, new_entity['name'], new_entity['level6'], new_relation_id,
 58 |                 100 * baseline_area_not_shared, 100 * new_area_not_shared)
 59 |             )
 60 |             messages_sent += 1
 61 | 
 62 |     for baseline_relation_id, baseline_entity in baseline_entities.items():
 63 |         if messages_sent > 10:
 64 |             telegram_sendtext('{0} refreshed and compared with {1}, but there are more than 10 regressions, stopping with sending'.format(
 65 |                 diff_type, entity_type
 66 |             ))
 67 |             break
 68 |         if baseline_relation_id not in new_entities:
 69 |             telegram_sendtext('{0} refreshed. Relation {1} ({2} {3}) existed before and it doesn\'t exist now.'.format(
 70 |                 diff_type, baseline_relation_id, entity_type, new_entity['name']
 71 |             ))
 72 |             messages_sent += 1
 73 | 
 74 |     return messages_sent
 75 | 
 76 | 
 77 | def main():
 78 |     if len(sys.argv) != 5:
 79 |         print("Not enough arguments, quitting")
 80 |         exit()
 81 |     diff_type = sys.argv[1].upper()
 82 |     if diff_type not in ('CADASTRE', 'OSM'):
 83 |         print('First argument (diff type) need to be Cadastre or OSM')
 84 |         exit()
 85 |     entity_type = sys.argv[2]
 86 |     if entity_type not in ('level8', 'level9'):
 87 |         print('Second argument (entity type) need to be level8 or level9')
 88 |         exit()
 89 | 
 90 |     baseline_csv = sys.argv[3]
 91 |     new_csv = sys.argv[4]
 92 |     messages_sent = process(diff_type, entity_type, baseline_csv, new_csv)
 93 |     if messages_sent == 0:
 94 |         telegram_sendtext(f'Cadastre analysis done for {entity_type} {diff_type} diff type for '
 95 |                           f'{datetime.date.strftime(datetime.date.today(), "%d.%m.%Y")}')
 96 | 
 97 | 
 98 | if __name__ == '__main__':
 99 |     main()
100 | 


--------------------------------------------------------------------------------
/extras/add_subarea_settlements.py:
--------------------------------------------------------------------------------
  1 | """
  2 | This script semi-automatically adds subarea level9 entities to level8 entities.
  3 | """
  4 | import os
  5 | import sys
  6 | 
  7 | import osmapi
  8 | import overpy
  9 | import yaml
 10 | 
 11 | current = os.path.dirname(os.path.realpath(__file__))
 12 | parent = os.path.dirname(current)
 13 | sys.path.append(parent)
 14 | 
 15 | from common import get_polygon_by_cadastre_id, load_level9_features
 16 | 
 17 | # Simple optimization not to get relation id for all settlements
 18 | # if number of subareas == number of settlements in municipality
 19 | ASSUME_SUBAREA_EQUAL_IF_EQUAL_NUMBER = True
 20 | 
 21 | 
 22 | def get_level9_from_osm(config, overpass_api, level9_ids):
 23 |     level9_features = {}
 24 |     i = 0
 25 |     for level9_id in level9_ids:
 26 |         i = i + 1
 27 |         print(f'Fetching level9 id: {level9_id}')
 28 |         _, osm_relation_name, osm_relation_id, _ = get_polygon_by_cadastre_id(overpass_api, admin_level=9, cadastre_id=level9_id, country=config['country'], id_key=config['level9_ref_key'])
 29 |         print('    ({}/{}) Found level 9: {}'.format(i, len(level9_ids), osm_relation_name))
 30 |         level9_features[osm_relation_id] = osm_relation_name
 31 |     return level9_features
 32 | 
 33 | 
 34 | def main(config, overpass_api, input_csv_file):
 35 |     api = osmapi.OsmApi(passwordfile='osm-password',
 36 |                         changesetauto=True, changesetautosize=20, changesetautotags=
 37 |                         {u"comment": u"OSM admin boundary conflation - adding missing subarea",
 38 |                          u"tag": u"mechanical=yes", u"source": config['changeset_source']})
 39 | 
 40 |     level9_features = load_level9_features(input_csv_file)
 41 |     level8_ids = set([level9_feature['level8_id'] for level9_feature in level9_features])
 42 | 
 43 |     counter = 0
 44 |     for level8_id in level8_ids:
 45 |         level9_ids = set([level9_feature['level9_id'] for level9_feature in level9_features if level9_feature['level8_id'] == level8_id])
 46 |         counter = counter + 1
 47 |         _, _, osm_relation_id, _ = get_polygon_by_cadastre_id(overpass_api, 8, level8_id, country=config['country'], id_key=config['level8_ref_key'])
 48 |         if osm_relation_id is None:
 49 |             print(f'Skipping level8 with id {level8_id}, not found in OSM')
 50 |             continue
 51 |         level8_feature = api.RelationGet(osm_relation_id)
 52 |         print('Processing level 8 {}'.format(level8_feature['tag']['name']))
 53 |         subarea_refs = [m for m in level8_feature['member'] if m['role'] == 'subarea']
 54 |         if ASSUME_SUBAREA_EQUAL_IF_EQUAL_NUMBER and len(subarea_refs) == len(level9_ids):
 55 |             print(f'({counter}/{len(level8_ids)}) Skipping {level8_feature["tag"]["name"]} '
 56 |                   f'object as it seems it already have all ({len(subarea_refs)}) subareas')
 57 |             continue
 58 |         level9_osm_features_in_this_level8 = get_level9_from_osm(overpass_api, level9_ids)
 59 |         anything_changed = False
 60 |         # Delete those that do not exist anymore
 61 |         for subarea_ref in subarea_refs:
 62 |             if subarea_ref['ref'] not in level9_osm_features_in_this_level8:
 63 |                 input('Removing subarea rel https://www.openstreetmap.org/relation/{} from municipality {}, confirm?'.
 64 |                       format(subarea_ref['ref'], level8_feature['tag']['name']))
 65 |                 level8_feature['member'].remove(subarea_ref)
 66 |                 anything_changed = True
 67 |         # Add those that do not exist
 68 |         for level9_osm_id in level9_osm_features_in_this_level8.keys():
 69 |             if level9_osm_id not in [m['ref'] for m in subarea_refs]:
 70 |                 # TODO: this is none, investigate
 71 |                 print('Adding settlement {} https://www.openstreetmap.org/relation/{} to municipality {}'.format(
 72 |                     level9_osm_features_in_this_level8[level9_osm_id], level9_osm_id, level8_feature['tag']['name']))
 73 |                 level8_feature['member'].append({'type': 'relation', 'ref': level9_ids, 'role': 'subarea'})
 74 |                 anything_changed = True
 75 |         if anything_changed:
 76 |             accepted = False
 77 |             while True:
 78 |                 response = input(
 79 |                     '({0}/{1}) Are you sure you want to update level 8 {2} (Y/n/c)?'.format(
 80 |                         counter, len(level8_ids), level8_feature['tag']['name']))
 81 |                 if response == '' or response.lower() == 'y':
 82 |                     accepted = True
 83 |                 if response.lower() == u'c':
 84 |                     new_answer = input('Again: ')
 85 |                     if new_answer == '':
 86 |                         continue
 87 |                     else:
 88 |                         accepted = True
 89 |                 break
 90 |             if accepted:
 91 |                 api.RelationUpdate(level8_feature)
 92 |                 api.flush()
 93 | 
 94 | 
 95 | if __name__ == '__main__':
 96 |     with open('config.yml', 'r') as config_yml_file:
 97 |         config = yaml.safe_load(config_yml_file)
 98 | 
 99 |     overpass_api = overpy.Overpass(url=config['overpass_url'])
100 | 
101 |     if len(sys.argv) != 2:
102 |         print("Usage: ./extras/add_subarea_level9_to_osm.py <input_csv_file>")
103 |         exit()
104 |     input_csv_file = sys.argv[1]
105 |     main(config, overpass_api, input_csv_file)
106 | 


--------------------------------------------------------------------------------
/common.py:
--------------------------------------------------------------------------------
  1 | import csv
  2 | import functools
  3 | import http.client
  4 | import socket
  5 | import sys
  6 | import time
  7 | import urllib.error
  8 | from collections import OrderedDict
  9 | 
 10 | import shapely.geometry as geometry
 11 | from overpy.exception import OverpassTooManyRequests, OverpassGatewayTimeout, OverpassUnknownContentType
 12 | from shapely.ops import linemerge, unary_union, polygonize
 13 | 
 14 | csv.field_size_limit(sys.maxsize)
 15 | 
 16 | 
 17 | def retry_on_error(timeout_in_seconds=60):
 18 |     def decorate(func):
 19 |         def call(*args, **kwargs):
 20 |             retries = 5
 21 |             while retries > 0:
 22 |                 try:
 23 |                     result = func(*args, **kwargs)
 24 |                 except (ConnectionRefusedError, ConnectionResetError,
 25 |                         OverpassTooManyRequests, OverpassGatewayTimeout, OverpassUnknownContentType,
 26 |                         socket.timeout, urllib.error.URLError, http.client.RemoteDisconnected):
 27 |                     retries = retries - 1
 28 |                     print('Connection refused, retrying')
 29 |                     time.sleep(timeout_in_seconds)
 30 |                     continue
 31 |                 return result
 32 |             raise Exception('Exhausted retries for connection refused, quitting')
 33 |         return call
 34 |     return decorate
 35 | 
 36 | 
 37 | def create_geometry_from_osm_response(relation, response):
 38 |     # Try to build shapely polygon out of this data
 39 |     outer_ways = [way.ref for way in relation.members if way.role == 'outer']
 40 |     inner_ways = [way.ref for way in relation.members if way.role == 'inner']
 41 |     lss = []
 42 |     for ii_w, way in enumerate(response.ways):
 43 |         if way.id not in outer_ways:
 44 |             continue
 45 |         ls_coords = []
 46 |         for node in way.nodes:
 47 |             ls_coords.append((node.lon, node.lat))
 48 |         lss.append(geometry.LineString(ls_coords))
 49 | 
 50 |     merged = linemerge([*lss])
 51 |     borders = unary_union(merged)
 52 |     polygons = list(polygonize(borders))
 53 |     print('polygons found {0}'.format(len(polygons)))
 54 |     polygon = functools.reduce(lambda p,x: p.union(x), polygons[1:], polygons[0])
 55 |     if len(inner_ways) > 0:
 56 |         lss_inner = []
 57 |         for ii_w, way in enumerate(response.ways):
 58 |             if way.id not in inner_ways:
 59 |                 continue
 60 |             ls_coords = []
 61 |             for node in way.nodes:
 62 |                 ls_coords.append((node.lon, node.lat))
 63 |             lss_inner.append(geometry.LineString(ls_coords))
 64 |         merged = linemerge([*lss_inner])
 65 |         borders = unary_union(merged)
 66 |         inner_polygons = list(polygonize(borders))
 67 |         for inner_polygon in inner_polygons:
 68 |             polygon = polygon.symmetric_difference(inner_polygon)
 69 |     return polygon
 70 | 
 71 | 
 72 | @retry_on_error(timeout_in_seconds=2*60)
 73 | def get_polygon_by_cadastre_id(api, admin_level, cadastre_id, country, id_key):
 74 |     response = api.query("""
 75 |     area["name"="{0}"]["admin_level"=2]->.c;
 76 |     relation(area.c)["admin_level"={1}]["{2}"={3}];
 77 |     (._;>;);
 78 |     out;
 79 |     // &contact=https://github.com/stalker314314/osm-admin-boundary-conflation/
 80 |     """.format(country, admin_level, id_key, cadastre_id))
 81 |     print('relations found for cadastre id {0}: {1}'.format(cadastre_id, len(response.relations)))
 82 |     national_border = any([w.tags['admin_level'] == '2' if 'admin_level' in w.tags else False for w in response.ways])
 83 |     if len(response.relations) != 1:
 84 |         return None, None, None, None
 85 |     polygon = create_geometry_from_osm_response(response.relations[0], response)
 86 |     return polygon, response.relations[0].tags['name'], response.relations[0].id, national_border
 87 | 
 88 | 
 89 | def load_level9_features(input_csv_file):
 90 |     """
 91 |     List of all level9 features with their name, id and (level8, level7, level6) names and ids
 92 |     """
 93 |     level9_features = []
 94 |     with open(input_csv_file) as input_csv:
 95 |         reader = csv.DictReader(input_csv)
 96 |         for row in reader:
 97 |             level9_features.append({
 98 |                 'level9_id': row['level9_id'],
 99 |                 'level9_name': row['level9_name'],
100 |                 'level8_id': row['level8_id'],
101 |                 'level8_name': row['level8_name'],
102 |                 'level7_id': row['level7_id'],
103 |                 'level7_name': row['level7_name'],
104 |                 'level6_id': row['level6_id'],
105 |                 'level6_name': row['level6_name'],
106 |                 'wkt': row['wkt'],
107 |             })
108 |     return level9_features
109 | 
110 | 
111 | def get_municipality_settlements():
112 |     """
113 |     :return: Map of level8_id => list(level8 entities)
114 |     """
115 |     municipality_settlements = {}
116 |     municipality_names = {}
117 |     with open('input/naselje.csv') as settlement_csv:
118 |         reader = csv.DictReader(settlement_csv)
119 |         for row in reader:
120 |             if row['opstina_maticni_broj'] not in municipality_names:
121 |                 municipality_names[row['opstina_maticni_broj']] = row['opstina_ime']
122 |             if row['opstina_maticni_broj'] not in municipality_settlements:
123 |                 municipality_settlements[row['opstina_maticni_broj']] = []
124 |             municipality_settlements[row['opstina_maticni_broj']].append(row['naselje_maticni_broj'])
125 |     municipality_settlements = OrderedDict(sorted(municipality_settlements.items(), key=lambda x: x))
126 |     return municipality_settlements
127 | 
128 | 
129 | def get_settlement_municipality():
130 |     """
131 |     :return: Map of level9_id => level8_id
132 |     """
133 |     settlements_municipality = {}
134 |     with open('input/naselje.csv') as naselja_csv:
135 |         reader = csv.DictReader(naselja_csv)
136 |         for row in reader:
137 |             settlements_municipality[int(row['naselje_maticni_broj'])] = int(row['opstina_maticni_broj'])
138 |     return settlements_municipality
139 | 
140 | 
141 | def get_municipality_district():
142 |     """
143 |     :return: Map of level8_id => level6
144 |     """
145 |     municipality_district = {}
146 |     with open('input/opstina.csv') as naselja_csv:
147 |         reader = csv.DictReader(naselja_csv)
148 |         for row in reader:
149 |             municipality_district[int(row['opstina_maticni_broj'])] = int(row['okrug_sifra'])
150 |     return municipality_district
151 | 
152 | 
153 | def get_district_name_by_id():
154 |     """
155 |     :return: Map of level6_id => level6
156 |     """
157 |     districts = {}
158 |     with open('input/opstina.csv') as naselja_csv:
159 |         reader = csv.DictReader(naselja_csv)
160 |         for row in reader:
161 |             districts[int(row['okrug_sifra'])] = row['okrug_ime']
162 |     return districts
163 | 


--------------------------------------------------------------------------------
/serbia/serbia2input.py:
--------------------------------------------------------------------------------
  1 | """
  2 | This script generate input files in proper CSV format
  3 | """
  4 | 
  5 | import csv
  6 | import os
  7 | import shutil
  8 | import sys
  9 | import time
 10 | import zipfile
 11 | 
 12 | import pyproj
 13 | import requests
 14 | from bs4 import BeautifulSoup
 15 | from shapely import wkt
 16 | from shapely.ops import transform
 17 | 
 18 | csv.field_size_limit(sys.maxsize)
 19 | 
 20 | wgs84 = pyproj.CRS('EPSG:4326')
 21 | utm = pyproj.CRS('EPSG:32634')
 22 | project = pyproj.Transformer.from_crs(utm, wgs84, always_xy=True).transform
 23 | 
 24 | 
 25 | def reproject_wkt(wkt_text):
 26 |     wkt_obj = wkt.loads(wkt_text)
 27 |     return transform(project, wkt_obj)
 28 | 
 29 | 
 30 | def download_cadastre_data(username, password):
 31 |     """
 32 |     Logs in to opendata.geosrbija.rs and downloads zips with data.
 33 |     It will clean zip files and leave input/naselje.csv which contains level9 data.
 34 |     """
 35 |     s = requests.Session()
 36 |     # Go to login page
 37 |     r = s.get('https://opendata.geosrbija.rs/loginopendata')
 38 |     soup = BeautifulSoup(r.text, 'lxml')
 39 |     csrf_token = soup.select_one('#csrf_token')['value']
 40 | 
 41 |     # Login
 42 |     headers = {}
 43 |     headers['content-type'] = 'application/x-www-form-urlencoded'
 44 |     r = s.post('https://opendata.geosrbija.rs/loginopendata', headers=headers,
 45 |                data={'username': username, 'password': password, 'csrf_token': csrf_token})
 46 | 
 47 |     if not os.path.exists('input'):
 48 |         os.mkdir('input')
 49 | 
 50 |     # Get okrug
 51 |     print('Downloading level6 data')
 52 |     r = s.get('https://opendata.geosrbija.rs/okrug?f=csv&user={0}'.format(username), stream=True)
 53 |     with open('input/okrug.zip', 'wb') as fd:
 54 |         for chunk in r.iter_content(chunk_size=1023):
 55 |             fd.write(chunk)
 56 |     with zipfile.ZipFile('input/okrug.zip', 'r') as zip_ref:
 57 |         zip_ref.extractall('./input')
 58 |     os.remove('input/okrug.zip')
 59 |     time.sleep(5)
 60 | 
 61 |     # Get grad
 62 |     print('Downloading level7 data')
 63 |     r = s.get('https://opendata.geosrbija.rs/gradovi?f=csv&user={0}'.format(username), stream=True)
 64 |     with open('input/grad.zip', 'wb') as fd:
 65 |         for chunk in r.iter_content(chunk_size=1024):
 66 |             fd.write(chunk)
 67 |     with zipfile.ZipFile('input/grad.zip', 'r') as zip_ref:
 68 |         zip_ref.extractall('./input')
 69 |     os.remove('input/grad.zip')
 70 |     time.sleep(5)
 71 | 
 72 |     # Get opstina
 73 |     print('Downloading level8 data')
 74 |     r = s.get('https://opendata.geosrbija.rs/opstina?f=csv&user={0}'.format(username), stream=True)
 75 |     with open('input/opstina.zip', 'wb') as fd:
 76 |         for chunk in r.iter_content(chunk_size=1024):
 77 |             fd.write(chunk)
 78 |     with zipfile.ZipFile('input/opstina.zip', 'r') as zip_ref:
 79 |         zip_ref.extractall('./input')
 80 |     os.remove('input/opstina.zip')
 81 |     time.sleep(5)
 82 | 
 83 |     # Get naselje
 84 |     print('Downloading level9 data')
 85 |     r = s.get('https://opendata.geosrbija.rs/naselje?f=csv&user={0}'.format(username), stream=True)
 86 |     with open('input/naselje.zip', 'wb') as fd:
 87 |         for chunk in r.iter_content(chunk_size=1024):
 88 |             fd.write(chunk)
 89 |     with zipfile.ZipFile('input/naselje.zip', 'r') as zip_ref:
 90 |         source = zip_ref.open('tmp/data/ready/naselja/naselje.csv')
 91 |         target = open('./input/naselje.csv', "wb")
 92 |         with source, target:
 93 |             shutil.copyfileobj(source, target)
 94 |     os.remove('input/naselje.zip')
 95 |     time.sleep(5)
 96 | 
 97 | 
 98 | def load_level9_features():
 99 |     level9_features = []
100 |     with open('input/naselje.csv') as level9_csv:
101 |         reader = csv.DictReader(level9_csv)
102 |         for row in reader:
103 |             level9_features.append({
104 |                 'level9_name': row['naselje_ime'],
105 |                 'level9_id': row['naselje_maticni_broj'],
106 |                 'level8_id': row['opstina_maticni_broj'],
107 |                 'wkt': reproject_wkt(row['wkt'])
108 |             })
109 |     return level9_features
110 | 
111 | 
112 | def write_level9_features(level9, output_csv_filename):
113 |     with open(output_csv_filename, 'w') as out_csv:
114 |         writer = csv.DictWriter(out_csv, fieldnames=['level9_id', 'level9_name', 'level8_id', 'level8_name', 'level7_id', 'level7_name', 'level6_id', 'level6_name', 'wkt'])
115 | 
116 |         writer.writeheader()
117 |         for data in level9:
118 |             writer.writerow(data)
119 | 
120 | 
121 | # Map of level8_id => (level8_name, level6_id)
122 | def load_level8_features() -> dict:
123 |     level8_features = {}
124 |     with open('input/opstina.csv') as level8_csv:
125 |         reader = csv.DictReader(level8_csv)
126 |         for row in reader:
127 |             level8_id = row['opstina_maticni_broj']
128 |             level8_name = row['opstina_ime']
129 |             level6_id = row['okrug_sifra']
130 |             level8_features[level8_id] = (level8_name, level6_id)
131 |     return level8_features
132 | 
133 | 
134 | # Map of level6_id => level6_name
135 | def load_level6_features() -> dict:
136 |     level6_features = {}
137 |     with open('input/okrug.csv') as level6_csv:
138 |         reader = csv.DictReader(level6_csv)
139 |         for row in reader:
140 |             level6_id = row['okrug_sifra']
141 |             level6_name = row['okrug_ime']
142 |             level6_features[level6_id] = level6_name
143 |     return level6_features
144 | 
145 | 
146 | def main(output_csv_file: str):
147 |     if not os.path.exists('rgz-password'):
148 |         print('Please create file rgz-password with RGZ credentials in the form of <username>:<password> in it')
149 |         exit()
150 |     with open('rgz-password') as f:
151 |         line = f.readline()
152 |     username = line.split(":")[0].strip()
153 |     password = line.split(":")[1].strip()
154 |     download_cadastre_data(username, password)
155 | 
156 |     print('Merging level9 data')
157 |     level9_features = load_level9_features()
158 |     level8_features = load_level8_features()
159 |     level6_features = load_level6_features()
160 |     for level9_feature in level9_features:
161 |         level9_feature['level8_name'] = level8_features[level9_feature['level8_id']][0]
162 |         level9_feature['level7_id'] = None
163 |         level9_feature['level7_name'] = None
164 |         level9_feature['level6_id'] = level8_features[level9_feature['level8_id']][1]
165 |         level9_feature['level6_name'] = level6_features[level9_feature['level6_id']]
166 |     print(f'Writing level9 data to {output_csv_file}')
167 |     write_level9_features(level9_features, output_csv_file)
168 |     print('Done')
169 | 
170 | 
171 | if __name__ == '__main__':
172 |     if len(sys.argv) != 2:
173 |         print("Usage: ./serbia2input.py <output_csv_file>")
174 |         exit()
175 |     output_csv_file = sys.argv[1]
176 |     main(output_csv_file)
177 | 


--------------------------------------------------------------------------------
/measure_quality.py:
--------------------------------------------------------------------------------
  1 | import csv
  2 | import multiprocessing
  3 | import os
  4 | import sys
  5 | import time
  6 | from concurrent.futures import ProcessPoolExecutor, as_completed
  7 | from threading import Lock
  8 | 
  9 | import overpy
 10 | import yaml
 11 | from shapely.wkt import loads
 12 | 
 13 | from common import retry_on_error, create_geometry_from_osm_response, get_polygon_by_cadastre_id, load_level9_features
 14 | 
 15 | csv.field_size_limit(sys.maxsize)
 16 | csv_write_mutex = Lock()
 17 | results = []
 18 | 
 19 | 
 20 | @retry_on_error()
 21 | def get_level9_polygon_by_name(api, country, level6_name, level8_name):
 22 |     for admin_level in (8, 7):
 23 |         response = api.query("""
 24 | area["name"="{0}"]["admin_level"=2]->.country;
 25 | (
 26 | 	area(area.country)["name"~"{1}$", i]["admin_level"={2}]->.district;
 27 |   	(
 28 |   		relation(area.district)["boundary"="administrative"]["admin_level"=9]["name"~"^{3}$", i];
 29 |     );
 30 | );
 31 | (._;>;);
 32 | out;
 33 | // &contact=https://github.com/stalker314314/osm-admin-boundary-conflation/
 34 |     """.format(country, level6_name, admin_level, level8_name))
 35 |         time.sleep(10)
 36 | 
 37 |         print('relations found for level {0}: {1}'.format(admin_level, len(response.relations)))
 38 |         if len(response.relations) != 1:
 39 |             continue
 40 |         polygon = create_geometry_from_osm_response(response.relations[0], response)
 41 |         return polygon, response.relations[0].tags['name'], response.relations[0].id
 42 |     return None, None, None
 43 | 
 44 | 
 45 | def get_current_results(output_file):
 46 |     # Load saved state
 47 |     results = []
 48 |     if os.path.isfile(output_file):
 49 |         with open(output_file) as csvfile:
 50 |             reader = csv.DictReader(csvfile)
 51 |             for row in reader:
 52 |                 results.append(
 53 |                     {'level6_name': row['level6_name'], 'level8_name': row['level8_name'],
 54 |                      'level9_name': row['level9_name'], 'osm_settlement_name': row['osm_settlement_name'],
 55 |                      'relation_id': row['relation_id'], 'area_diff': row['area_diff'],
 56 |                      'i_o_u': row['i_o_u'], 'national_border': row['national_border']})
 57 |     return results
 58 | 
 59 | 
 60 | def write_results(current_results, output_file):
 61 |     with csv_write_mutex:
 62 |         with open(output_file, 'w') as out_csv:
 63 |             writer = csv.DictWriter(out_csv, fieldnames=[
 64 |                 'level6_name', 'level8_name', 'level9_name', 'osm_settlement_name',
 65 |                 'relation_id', 'area_diff', 'i_o_u', 'national_border'])
 66 |             writer.writeheader()
 67 |             for data in current_results:
 68 |                 writer.writerow(data)
 69 | 
 70 | 
 71 | def process_level9(config, overpass_api, level9_entity, count_processed, total_to_process):
 72 |     global results
 73 |     print('Processed {0}/{1}'.format(count_processed, total_to_process))
 74 | 
 75 |     country = config['country']
 76 |     level9_ref_key = config['level9_ref_key']
 77 | 
 78 |     cadastre_level9_polygon = loads(level9_entity['wkt'])
 79 |     level6_name = level9_entity['level6_name']
 80 |     level8_name = level9_entity['level8_name']
 81 |     level9_name = level9_entity['level9_name']
 82 |     level9_id = level9_entity['level9_id']
 83 | 
 84 |     print('Processing {0} {1}'.format(level8_name, level9_name))
 85 | 
 86 |     overpass_level9_polygon, osm_settlement_name, osm_relation_id, national_border = \
 87 |         get_polygon_by_cadastre_id(overpass_api, admin_level=9, cadastre_id=level9_id, country=country, id_key=level9_ref_key)
 88 |     if overpass_level9_polygon is None:
 89 |         print(f'Level 8 {level8_name} and level 9 {level9_name} not found using {level9_ref_key}')
 90 |         overpass_level9_polygon, osm_settlement_name, osm_relation_id, national_border = \
 91 |             get_level9_polygon_by_name(overpass_api, country, level8_name, level9_name)
 92 |         if overpass_level9_polygon is None:
 93 |             print(f'Level8 {level8_name} and level9 {level9_name} not found at all')
 94 |             result = {'level6_name': level6_name, 'level8_name': level8_name, 'level9_name': level9_name,
 95 |                       'osm_settlement_name': '', 'relation_id': -1, 'area_diff': -1, 'i_o_u': -1,
 96 |                       'national_border': national_border}
 97 |             results.append(result)
 98 |             return result
 99 | 
100 |     intersection = cadastre_level9_polygon.intersection(overpass_level9_polygon)
101 |     union = cadastre_level9_polygon.union(overpass_level9_polygon)
102 |     i_o_u = intersection.area / union.area
103 | 
104 |     print(level8_name, level9_name, osm_settlement_name, 100 * intersection.area/cadastre_level9_polygon.area, i_o_u)
105 |     result = {'level6_name': level6_name, 'level8_name': level8_name, 'level9_name': level9_name,
106 |               'osm_settlement_name': osm_settlement_name, 'relation_id': osm_relation_id,
107 |               'area_diff': round(intersection.area/cadastre_level9_polygon.area, 5),
108 |               'i_o_u': round(i_o_u, 5),
109 |               'national_border': national_border}
110 |     results.append(result)
111 |     return result
112 | 
113 | 
114 | def measure_quality(config, overpass_api, input_csv_file, output_file):
115 |     global results
116 |     results = get_current_results(output_file)
117 |     level9_features = load_level9_features(input_csv_file)
118 | 
119 |     count_processed = 1
120 |     all_futures = []
121 |     thread_count = 1 if 'localhost' not in overpass_api.url else multiprocessing.cpu_count()
122 |     print('Using {0} threads'.format(thread_count))
123 |     with ProcessPoolExecutor(max_workers=thread_count) as executor:
124 |         for level9_feature in level9_features:
125 |             # Skip if already processed
126 |             level8_name = level9_feature['level8_name']
127 |             level9_name = level9_feature['level9_name']
128 |             if any((r for r in results if r['level8'] == level8_name and r['level9'] == level9_name)):
129 |                 print('Level8 {0} and level9 {1} already processed'.format(level8_name, level9_name))
130 |                 continue
131 | 
132 |             future = executor.submit(process_level9, config, overpass_api, level9_feature, count_processed, len(level9_features))
133 |             all_futures.append(future)
134 |             count_processed = count_processed + 1
135 |         for future in as_completed(all_futures):
136 |             results.append(future.result())
137 |     write_results(results, output_file)
138 | 
139 | 
140 | if __name__ == '__main__':
141 |     with open('config.yml', 'r') as config_yml_file:
142 |         config = yaml.safe_load(config_yml_file)
143 | 
144 |     overpass_api = overpy.Overpass(url=config['overpass_url'])
145 | 
146 |     if len(sys.argv) != 3:
147 |         print("Usage: ./measure_quality.py <input_csv_file> <output_csv_file>")
148 |         exit()
149 |     input_csv_file = sys.argv[1]
150 |     output_csv_file = sys.argv[2]
151 |     measure_quality(config, overpass_api, input_csv_file, output_csv_file)
152 | 


--------------------------------------------------------------------------------
/conflate-report.py:
--------------------------------------------------------------------------------
 1 | import pickle
 2 | import pprint
 3 | import sys
 4 | from collections import OrderedDict
 5 | 
 6 | from jinja2 import Environment, FileSystemLoader
 7 | 
 8 | from processing_state import ProcessingState
 9 | 
10 | errors = {
11 |     ProcessingState.NO: 'Not yet considered.',
12 |     ProcessingState.CHECKED_POSSIBLE: 'Checked and way can be conflated without problems, but conflation not yet done.',
13 |     ProcessingState.CONFLATED: 'Conflated (already done).',
14 |     ProcessingState.ERROR_END_POINTS_FAR_APART: 'First or last node from cadastre and OSM are too far apart. This can happen when way between two entities is split. Additional context is mentioning exact distance they are apart.',
15 |     ProcessingState.ERROR_GEOMETRY_WRONG: 'User rejected conflation.',
16 |     ProcessingState.ERROR_SHARED_WAY_NOT_FOUND: 'Way to be conflated is shared between two entities, but no such way is found in OSM. This should not be common situation and it might mean that border in OSM is converted to single node or that entities to not touch at all. diruju. This error requires human investigation.',
17 |     ProcessingState.ERROR_WAY_NOT_FOUND: 'Way to be conflated is touching only one entity, but no such way is found in OSM. This might mean that border between two entites from cadastre have a gap, but in there is no gap in OSM and border in OSM is shared (and it should not be). Human need to find this situation and split border to two separate ways.',
18 |     ProcessingState.ERROR_MULTIPLE_SHARED_WAYS: 'Way to be conflated is shared between two entities, but in OSM there are multiple such shared ways. They should probably be merged (unless there are lower level admin boundaries conected to them). Additional context is listing all found OSM ways.',
19 |     ProcessingState.ERROR_MULTIPLE_SINGLE_WAY: 'Way to be conflated is touching only one entity, but in OSM there are multiple such single ways. They should probably be merged (unless there are lower level admin boundaries conected to them). Additional context is listing all found OSM ways.',
20 |     ProcessingState.ERROR_NODES_WITH_TAGS: 'Some nodes in found way do contain unexpected tags. Human need to check these tags and either remove them, or ungle those nodes from way. Additional context is listing all those nodes.',
21 |     ProcessingState.ERROR_NATIONAL_BORDER: 'Found way is national border (admin_level=2) and no conflation is possible. This is kind of error that is not fixable without further discussion between two national communities.',
22 |     ProcessingState.ERROR_UNEXPECTED_TAG: 'Found way contains unexpected tags. Human need to either remove those tags or split way into two different ways. Additional context is listing those tags.',
23 |     ProcessingState.ERROR_NODE_IN_OTHER_WAYS: 'Found way is containing node that is shared with some other ways that are not administrative borders. Sometimes they should be unglued, sometimes it is actually untagged border. Additional context is listing those other ways.',
24 |     ProcessingState.ERROR_NODE_IN_NATIONAL_BORDER: 'Found way contains node that is shared with national border and it should not be moved. Additional context is listing way of national border.',
25 |     ProcessingState.ERROR_NODE_IN_OTHER_RELATION: 'Found way contains node that is part of some other relation that is not administrative border and it should not be moved. Additional context contains that other relation.',
26 |     ProcessingState.ERROR_NODE_IN_NATIONAL_RELATION: 'Found way contains node that is part of national border and it should not be moved. Additional context contains tway of national border.',
27 |     ProcessingState.ERROR_INVALID_SHAPE: 'Invalid shape read from .osm file.',
28 |     ProcessingState.ERROR_CLOSED_SHAPE: 'Way to be conflated is closed shape (enclave or exclave). This tool does not support conflation of closed shaped yet. Human need to do manual conflation.',
29 |     ProcessingState.ERROR_OVERLAPPING_WAYS: 'Way to be conflated contains more than 2 entities. This means that some of the entities overlap which usually means error in cadastre data. Check manually or contact authoritative source.',
30 |     ProcessingState.ERROR_TOO_MANY_NODES: 'Way to be conflated contains more than 2000 nodes which is above OSM limit for number of nodes in the way. Please simplify this way manually.'
31 | }
32 | 
33 | errors = OrderedDict(sorted(errors.items(), key=lambda x: x[0].value))
34 | 
35 | 
36 | def main(progress_file, output_html_file):
37 |     env = Environment(loader=FileSystemLoader(searchpath='./templates'))
38 |     template = env.get_template('index_template.html')
39 | 
40 |     with open(progress_file, 'rb') as p:
41 |         source_data = pickle.load(p)
42 |     total_ways = len(source_data['ways'])
43 |     processed_ways = len([w for w in source_data['ways'].values() if w['processed'] != ProcessingState.NO])
44 |     ways_with_osm_ways_found = len([w for w in source_data['ways'].values() if w['osm_way'] is not None])
45 |     count_per_error = {}
46 |     for w in source_data['ways'].values():
47 |         if w['processed'] not in count_per_error:
48 |             count_per_error[w['processed']] = 0
49 |         count_per_error[w['processed']] += 1
50 |         if w['error_context'] is None:
51 |             w['error_context'] = ''
52 |         if w['processed'] in (ProcessingState.ERROR_MULTIPLE_SHARED_WAYS, ProcessingState.ERROR_MULTIPLE_SINGLE_WAY,
53 |                               ProcessingState.ERROR_NODE_IN_OTHER_WAYS, ProcessingState.ERROR_NODE_IN_NATIONAL_BORDER):
54 |             ways = w['error_context'].split(',')
55 |             w['error_context'] = ','.join(['<a href="https://www.openstreetmap.org/way/{0}" target="_blank">{0}</a>'.format(w) for w in ways]).replace('"', '\\"')
56 |         elif w['processed'] in (ProcessingState.ERROR_NODES_WITH_TAGS,):
57 |             nodes = w['error_context'].split(',')
58 |             w['error_context'] = ','.join(['<a href="https://www.openstreetmap.org/node/{0}" target="_blank">{0}</a>'.format(n) for n in nodes]).replace('"', '\\"')
59 |         elif w['processed'] in (ProcessingState.ERROR_NODE_IN_OTHER_RELATION,):
60 |             relations = w['error_context'].split(',')
61 |             w['error_context'] = ','.join(['<a href="https://www.openstreetmap.org/relation/{0}" target="_blank">{0}</a>'.format(r) for r in relations]).replace('"', '\\"')
62 |         elif w['processed'] in (ProcessingState.ERROR_END_POINTS_FAR_APART,):
63 |             w['error_context'] = '{:.2f}m'.format(float(w['error_context']))
64 |     print('Total ways: {0}'.format(total_ways))
65 |     print('Processed ways: {0}'.format(processed_ways))
66 |     print('Ways with OSM way found: {0}'.format(ways_with_osm_ways_found))
67 |     pp = pprint.PrettyPrinter(indent=4)
68 |     print('Count per error:\n{0}'.format(pp.pformat(count_per_error)))
69 |     count_per_error = OrderedDict(sorted(count_per_error.items(), key=lambda x: x[1], reverse=True))
70 | 
71 |     source_data = {k: source_data['ways'][k] for k in list(source_data['ways'])[0:-1]}
72 |     output = template.render(total_ways=total_ways, processed_ways=processed_ways, errors=errors,
73 |                              count_per_error=count_per_error, ways_with_osm_ways_found=ways_with_osm_ways_found,
74 |                              source_data=source_data)
75 |     with open(output_html_file, 'w', encoding='utf-8') as fh:
76 |         fh.write(output)
77 | 
78 | 
79 | if __name__ == '__main__':
80 |     if len(sys.argv) != 3:
81 |         print("Usage: ./conflate-report.py <progress_file> <output_html_file>")
82 |         exit()
83 |     progress_file = sys.argv[1]
84 |     output_html_file = sys.argv[2]
85 |     main(progress_file, output_html_file)
86 | 


--------------------------------------------------------------------------------
/templates/index_template.html:
--------------------------------------------------------------------------------
  1 | <!doctype html>
  2 | <html lang="en">
  3 | 
  4 | <head>
  5 |     <meta charset="utf-8">
  6 | 
  7 |     <title>OSM admin boundary conflation report</title>
  8 |     <meta name="description" content="OSM admin boundary conflation report">
  9 | 
 10 |     <link type="text/css" rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/jsgrid/1.5.3/jsgrid.min.css" />
 11 |     <link type="text/css" rel="stylesheet"
 12 |         href="https://cdnjs.cloudflare.com/ajax/libs/jsgrid/1.5.3/jsgrid-theme.min.css" />
 13 | </head>
 14 | 
 15 | <body>
 16 |     <h1>OSM admin boundary conflation report</h1>
 17 |     <a href="#" id="toggleLegend">Toggle legend</a>
 18 |     <div id="legend" style="display: none;">
 19 |     <p>Explanation of all columns in report<p>
 20 |         <ul>
 21 |             <li><strong>Way ID</strong> &mdash; ID of the way from .osm file. Not of great importance</li>
 22 |             <li><strong>Shared entities</strong> &mdash; One of two level 9 entities with which this way is sharing border</li>
 23 |             <li><strong>OSM Way</strong> &mdash; if we are sure we uniquely identified OSM way, it will be shown here</li>
 24 |             <li><strong>Conflation potential</strong> &mdash; is conflation done, is it possible and if not - why not</li>
 25 |             <li><strong>Additional context</strong> &mdash; if there is any conflation errors, here is additional context that can give more clarity and help in fixing problem</li>
 26 |         </ul>
 27 |         <p>List of all conflation errors:</p>
 28 |         <ul>
 29 |             {% for key, value in errors.items() %}
 30 |                 <li><strong>{{ key.name }}</strong> &mdash; {{ value }}</li>
 31 |             {% endfor %}
 32 |         </ul>
 33 |         <p>Statistics:</p>
 34 |         <ul>
 35 |             <li><strong>Total ways</strong> &mdash; {{ total_ways }}</li>
 36 |             <li><strong>Processed ways</strong> &mdash; {{ processed_ways}} </li>
 37 |             <li><strong>Ways found in OSM</strong> &mdash; {{ ways_with_osm_ways_found }}</li>
 38 |         </ul>
 39 |         <p>Statistics of conflation errors:</p>
 40 |         <ul>
 41 |             {% for key, value in count_per_error.items() %}
 42 |                 <li><strong>{{ key.name }}</strong> &mdash; {{ value }} ({{ "{:.2f}".format((100.0 * value) / total_ways) }}%)</li>
 43 |             {% endfor %}
 44 |         </ul>
 45 |     </div>
 46 |     <br/>
 47 |     <div id="jsGrid"></div>
 48 | 
 49 |     <script type="text/javascript" src="https://ajax.aspnetcdn.com/ajax/jQuery/jquery-2.2.4.min.js"></script>
 50 |     <script type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/jsgrid/1.5.3/jsgrid.min.js"></script>
 51 | 
 52 |     <script>
 53 |         $(document).ready(function () {
 54 |             $('#toggleLegend').click(function () {
 55 |                 $('#legend').slideToggle("slow");
 56 |             });
 57 |         });
 58 | 
 59 |         String.prototype.replaceAll = function (find, replace) {
 60 |             var str = this;
 61 |             return str.replace(new RegExp(find, 'g'), replace);
 62 |         };
 63 | 
 64 |         // Needed for easier search for Serbian language, but can be ignored for everyone else
 65 |         function transliterate(s) {
 66 |             return s.toLowerCase()
 67 |                 .replaceAll('а', 'a')
 68 |                 .replaceAll('б', 'b')
 69 |                 .replaceAll('в', 'v')
 70 |                 .replaceAll('г', 'g')
 71 |                 .replaceAll('д', 'd')
 72 |                 .replaceAll('ђ', 'dj')
 73 |                 .replaceAll('е', 'e')
 74 |                 .replaceAll('ж', 'z')
 75 |                 .replaceAll('з', 'z')
 76 |                 .replaceAll('и', 'i')
 77 | 
 78 |                 .replaceAll('ј', 'j')
 79 |                 .replaceAll('к', 'k')
 80 |                 .replaceAll('л', 'l')
 81 |                 .replaceAll('љ', 'lj')
 82 |                 .replaceAll('м', 'm')
 83 |                 .replaceAll('н', 'n')
 84 |                 .replaceAll('њ', 'nj')
 85 |                 .replaceAll('о', 'o')
 86 |                 .replaceAll('п', 'p')
 87 |                 .replaceAll('р', 'r')
 88 | 
 89 |                 .replaceAll('с', 's')
 90 |                 .replaceAll('т', 't')
 91 |                 .replaceAll('ћ', 'c')
 92 |                 .replaceAll('у', 'u')
 93 |                 .replaceAll('ф', 'f')
 94 |                 .replaceAll('х', 'h')
 95 |                 .replaceAll('ц', 'c')
 96 |                 .replaceAll('ч', 'c')
 97 |                 .replaceAll('џ', 'dz')
 98 |                 .replaceAll('ш', 's')
 99 | 
100 |                 .replaceAll('đ', 'dj')
101 |                 .replaceAll('ž', 'z')
102 |                 .replaceAll('ć', 'c')
103 |                 .replaceAll('č', 'c')
104 |                 .replaceAll('š', 's');
105 |         }
106 | 
107 |         var db = {
108 |             loadData: function(filter) {
109 |                 return $.grep(this.clients, function(client) {
110 | 
111 |                     return (!filter.error || client.error === filter.error)
112 |                         && (!filter.relations || client.relations_latin.toLowerCase().indexOf(transliterate(filter.relations)) > -1);
113 |                 });
114 |             },
115 |         };
116 | 
117 |         window.db = db;
118 | 
119 |         db.clients = [
120 | {# This is ugly and condensed because it shaves multiple MBs in produced HTML! #}
121 | {%- for way_id, way in source_data.items() %}
122 |     {"way_id": {{ way_id }},
123 |     "relations": "{{ way.relations }}",
124 |     "osm_way": {% if way.osm_way %}"<a href=\"https://www.openstreetmap.org/way/{{ way.osm_way }}\" target=\"_blank\">{{ way.osm_way }}</a>"{% else %}""{% endif %},
125 |     "error": "{{ way.processed.name }}",
126 |     "error_context": "{{ way.error_context }}"},
127 | {% endfor %}
128 |         ];
129 | 
130 |         db.errors = [
131 |             { Name: undefined, Id: undefined },
132 |             {% for key, value in errors.items() %}{ Name: "{{ key.name }}", Id: "{{ key.name }}" },{% endfor %}
133 |         ];
134 | 
135 |         db.clients.forEach(element => {
136 |             element['relations_latin'] = transliterate(element['relations']);
137 |         });
138 | 
139 |         $("#jsGrid").jsGrid({
140 |             width: "100%",
141 |             height: "auto",
142 | 
143 |             pageSize: 1000,
144 |             filtering: true,
145 |             inserting: false,
146 |             editing: false,
147 |             heading: true,
148 |             sorting: true,
149 |             paging: true,
150 |             selecting: false,
151 |             autoload: true,
152 | 
153 |             noDataContent: "Nothing found",
154 |             pagerFormat: "Pages: {first} {prev} {pages} {next} {last}    {pageIndex} of {pageCount}",
155 |             pagePrevText: "Previous",
156 |             pageNextText: "Next",
157 |             pageFirstText: "First",
158 |             pageLastText: "Last",
159 | 
160 |             controller: db,
161 | 
162 |             fields: [
163 |                 { name: "way_id", type: "text", width: 100, title: "Way ID", filtering: false },
164 |                 { name: "relations", type: "text", width: 300, title: "Shared entities", filtering: true },
165 |                 { name: "osm_way", type: "text", width: 100, title: "OSM Way", filtering: false },
166 |                 { name: "error", type: "select", items: db.errors, valueField: "Id", textField: "Name", title: "Conflation potential", width: 200, filtering: true },
167 |                 { name: "error_context", type: "text", width: 300, title: "Additional context", filtering: false },
168 |             ]
169 |         });
170 |     </script>
171 | </body>
172 | 
173 | </html>
174 | 


--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
  1 | # OSM administrative boundary conflation
  2 | 
  3 | This repo contains set of predefined pipelines, data formats and tools that aid conflation of
  4 | administrative boundaries in OpenStreetMap (OSM). If you get your hands on authoritative dataset ("external truth")
  5 | which contains geometries of admin boundaries, this repo can help you to import this data in an easy and semi-automated
  6 | way.
  7 | 
  8 | Conflation is hard and labor-intensive process if you want to do it properly. When conflating boundaries, you need to
  9 | take great care not to accidentally move national boundary, or move other glued ways like highways, or move tagged nodes,
 10 | like traffic lights. And you can have other relations glued together with administrative boundaries. It can get messy
 11 | and error-prone very fast. This repo helps with all of that and on high-level it will enable you to:
 12 | 
 13 | * measure quality of your boundaries (authoritative data vs OSM data)
 14 | * keep quality of OSM boundaries in daily, continuous fashion
 15 | * prepare data so you can do manual conflation using tools like JOSM
 16 | * check conflation potential (what can be semi-automatically conflated, what not and most importantly - why not)
 17 | * do ungluing and conflate boundary ways in semi-automatic ways (present to user each way to be conflated and result of
 18 | conflation and ask user to proceed)
 19 | 
 20 | ## Install
 21 | 
 22 | This repo is tested exclusively in Linux and is recommended way to use it. On Windows, your best bet is Conda.
 23 | Here are brief instructions for Debian:
 24 | ```
 25 | sudo apt install proj-bin libproj-dev curl gdal-bin git
 26 | python -m pip install -r requirements.txt 
 27 | ```
 28 | 
 29 | Also, you will need to install Docker if you plan to use local Overpass instance (which is highly encouraged). If you do
 30 | use Docker, do note that all scripts here assume that Docker could be ran without root, so try to set up Docker to be
 31 | rootless.
 32 | 
 33 | During running of some tools, scripts will try to clone ogr2osm repo (it is dependency, but there are no automated way
 34 | to pull this, so I added `git clone` directly in script to make your life easier).
 35 | 
 36 | ## Pipeline
 37 | 
 38 | ```
 39 |       Input data
 40 |           |
 41 |           v
 42 | +--------------------+
 43 | |                    |
 44 | |     Your script    |
 45 | |    to convert to   |
 46 | |     input .csv     |
 47 | |                    |
 48 | +----------+---------+
 49 |            | .csv
 50 |            |
 51 |            +-------------------------+
 52 |            |                         |
 53 |            v                         v
 54 | +--------------------+    +--------------------+
 55 | |                    |    |                    |
 56 | |                    |    |                    |
 57 | |  inputcsv2shp.py   |    | measure_quality.py |
 58 | |                    |    |                    |
 59 | |                    |    |                    |
 60 | +---------+----------+    +--------------------+
 61 |           |  .shp
 62 |           v
 63 | +--------------------+
 64 | |                    |
 65 | |                    |
 66 | |     shp2osm.py     |
 67 | |                    |
 68 | |                    |
 69 | +---------+----------+
 70 |           | .osm
 71 |           v
 72 | +--------------------+
 73 | |                    |
 74 | |                    |  conflate-progress.pickle
 75 | |    conflate.py     +---------------+
 76 | |                    |               |
 77 | |                    |               v
 78 | +---------+----------+    +-------------------+
 79 |           |               |                   |
 80 |           |Changesets     |                   |
 81 |           v               | conflate-stats.py |
 82 |        +-----+            |                   |
 83 |        |     |            |                   |
 84 |        | OSM |            +---------+---------+
 85 |        |     |                      |
 86 |        +-----+                      |.html
 87 |                                     v
 88 | ```
 89 | 
 90 | ## Usage
 91 | 
 92 | ### Adjust config
 93 | 
 94 | Root directory of this repo contains file `config.yml`. It contains most important configuration that you need to closely
 95 | go over and adopt to your use case. All fields should be self-explanatory, but if you are not sure about some, or need
 96 | more extensibility than what is there, let me know!
 97 | 
 98 | ### Convert input data to .CSV
 99 | This repo contains several tools to make sense of admin boundary conflation. First thing is to convert your input dataset
100 | to something that pipeline down the road can understand. This is simple CSV file which contains following columns:
101 | * `level9_id`: string
102 | * `wkt`: WKT geometry of your level 9 entity (in WSG84)
103 | 
104 | Everything else is optional:
105 | 
106 | * `level9_name`: string
107 | * `level8_id`: string
108 | * `level8_name`: string
109 | * `level7_id`: string
110 | * `level7_name`: string
111 | * `level6_id`: string
112 | * `level6_name`: string
113 | 
114 | As you can see, format is as simple as it can be. How to create it from your dataset is out of scope of this document,
115 | but you can use Python (look at implementation for Serbia located at `serbia/serbia2input.py`) or even QGIS. If you need
116 | help, feel free to ping me with your dataset or open issue on Github!
117 | 
118 | If you don't have level9 entities (settlements, neightbours), but something else (level 8, level 10...), script should
119 | work in theory, but it needs adjustments here and there. Let me know if this is blocker for you, so we can implement
120 | your use case too.
121 | 
122 | ### Measure quality
123 | 
124 | Once you have data in expected .csv format, you can run: `python ./measure_quality.py <input_csv_file> <output_csv_file>`
125 | and it will go over all entities and, for each admin entity, it will output IoU (intersection over union) as a standard
126 | measurement of how good authoritative dataset fit OSM data. It works by matching `ref` from your dataset to OSM or
127 | `name` tag, so if you don't have matching `ref` or `name` tags in OSM, it cannot match them. If you want easy way to add
128 | `ref` tags to OSM, check section "Extra scripts".
129 | 
130 | This script can measure around 1000-2000 entities per day if you use public Overpass instances. If you use local
131 | Overpass instance, it will work in parallel and can process 100000 entities per day (roughly 100x faster)!
132 | 
133 | If you don't plan to do conflation of your data, this measurement script is all you need. Check section "Daily
134 | measurement" to understand how you can do continuous checks for quality of your administrative boundaries.
135 | 
136 | ### Produce .osm file for conflation
137 | 
138 | Conflation is slow and semi-manual process. Before you can proceed, you need to convert input .csv format to .osm format
139 | with which tooling works. This is needed only once and it is automatic process using two scripts:
140 | ```
141 | python inputcsv2shp.py <input_csv_file> <intermediate_shp_file>
142 | ./shp2osm.sh <intermediate_shp_file> <output_osm_file>
143 | ```
144 | 
145 | You can open and inspect obtained .osm file in JOSM editor and check it. It should have separate ways for each segment
146 | of administrative boundary. Goal of conflation is now to find and conflate each of these segments to OSM. If you don't
147 | want to use conflate script, you can still use obtained .osm file to do it manually (see section "Manual conflation
148 | with .osm file").
149 | 
150 | ### Manual conflation with .osm file
151 | 
152 | **BIG FAT DISCLAIMER**: Please don't import data or change boundaries without fully conforming with
153 | [OSM import guidelines](https://wiki.openstreetmap.org/wiki/Import/Guidelines) *and* also consulting with both local
154 | community and neighboring countries' communities (if you plan to change national boundaries!).
155 | 
156 | * Install JOSM, and install plugin [UtilsPlugin2](https://josm.openstreetmap.de/wiki/Help/Plugin/UtilsPlugin2) which we
157 | will need during process of conflation
158 | * If .osm files are big, increase memory provided to JOSM. It boils down to add parameters `-J-d64 -J-Xmx2048m`, but
159 | check [here](https://josm.openstreetmap.de/wiki/Download#VMselectiononWindowsx64) for more details.
160 | * Open obtained .osm file in JOSM as new layer.
161 | * Go to "File"->"Download data" (Ctr+Shift+Down) and go to tab "Download from Overpass API" and input this[1] as a
162 | query. It is not important what you select in the map below. Click "Download as new layer". It is wise to uncheck "Zoom
163 | to downloaded data", so you don't zoom back to whole country. After download, you should get new layer "Data Layer 1".
164 | 
165 | Now that you set it all up, here is cyclic workflow:
166 | * Select "Data layer 1" layer and zoom to level9 entities that you want to fix. Focus on a particular way you want to
167 | fix.
168 | * Copy authoritative way to OSM layer. To do this, first select .osm layer, then select one or more ways. Copy it
169 | (Ctrl+C). Go back to "Data layer 1" and paste it at same position using  "Edit"->"Paste at source position" (Ctrl+Alt+V).
170 | Never do Ctrl+V!
171 | * Now select both old and new way, holding Ctrl. With both ways selected, choose "More Tools" -> "Replace Geometry"
172 | (Ctrl+Shift+G)
173 | * New dialog for solving conflicts will show up. You should "Keep" most tags, but you should "delete" "level9_id" tag.
174 | Sometimes, if you change boundary with lower "admin_level" (for example "admin_level=7"), you can have conflict for that
175 | tag too, but always choose lower number. Click "Apply".
176 | * You just conflated way from old (OSM) geometry to new (authoritative) geometry and all points are added/modified. From
177 | two ways, we got one. What is not fixed are end nodes. They are now detached from OSM boundaries and need to be
178 | reattached. To do that, move them to existing OSM way holding Ctrl to glue them. All boundaries always should form
179 | closed shape.
180 | * Congratulation, you just conflated your first way:)
181 | 
182 | [1]
183 | ```
184 | [out:xml];
185 | area["name"="<your_country>"]["admin_level"=2]->.a;
186 | (
187 | 	relation(area.a)["boundary"]["admin_level"];
188 | );
189 | (._;>;);
190 | out;
191 | ```
192 | 
193 | ### Assess and report conflating potential
194 | 
195 | If you just want to see what is possible to be automatically, set `config.yml` like this:
196 | ```
197 | dry_run: True
198 | auto_proceed: True
199 | ```
200 | 
201 | and run it like `python <input_osm_file> <progress_file>`. This will check each way and save intermediate results to
202 | `progress_file`. If you provide same progress file again, it will continue where it left of. If you want to start from
203 | scratch, provide new file or delete existing one.
204 | 
205 | This file can be used later to generate report of possible conflation, and if it is not possible - it will explain why
206 | it is not possible (there are lot of various reasons, all explained in report). To generate report, execute:
207 | ```
208 | python conflate-report.py <progress_file> <output_html_file>
209 | ```
210 | 
211 | When you open <output_html_file> in your browser, you can check individual problems and solve them independently.
212 | 
213 | ### Semi-automatic conflation
214 | 
215 | Once you assessed conflating potential, you might want to conflate those ways which are possible to be conflated. For
216 | that, set `config.yml` to:
217 | ```
218 | dry_run: False
219 | auto_proceed: False
220 | ```
221 | 
222 | You will need to create file named `osm-password` in root folder and fill it with one line that has
223 | `<osm_username>:<osm_password>` in it. This is needed to authenticate with OSM. Once you run conflation with
224 | `python <input_osm_file> <progress_file>`, you will be asked for those ways that can be conflated, new dialog will be
225 | shown with what geometry will be changed and you need to click "Y" for each way. It is wise to check what actual changes
226 | in OSM has been done, to be sure this script is not going crazy!
227 | 
228 | ### Extra scripts
229 | 
230 | There are couple of useful scripts in `extras/` folder which might come handy to you. They all require to create file
231 | named `osm-password` in root folder and fill it with one line that has `<osm_username>:<osm_password>` in it. They are:
232 | 
233 | * `add_level9_id_to_osm.py`: use it to mass add "ref" tag to OSM to all your level 9 entities, based on their name
234 | * `add_level8_id_to_osm.py`: use it to mass add "ref" tag to OSM to all your level 8 entities, based on their name
235 | * `add_subare_settlements.py`: use it to mass add level 9 relations to level 8 relations as a "subarea" members
236 | 
237 | ### Continuous quality checks
238 | 
239 | If you can measure quality of your level 9 entities, it should be easy to run that scripts in two consecutive days and
240 | do the difference on their outputs. This is what we did for Serbia and you can check `serbia/daily-measurement.sh` for
241 | details. Basically, we refresh cadastre data and OSM data for day before, then update data for today and do difference
242 | of their results and report if any level 9 entity is worse than it was day before. This way, we get continuous checks.
243 | 
244 | If you need something similar, but you are not sure how to do it, let me know and I will try to help you!
245 | 


--------------------------------------------------------------------------------
/translation.py:
--------------------------------------------------------------------------------
  1 | import geom
  2 | import yaml
  3 | 
  4 | import os
  5 | 
  6 | __location__ = os.path.dirname(os.path.realpath(__file__))
  7 | 
  8 | with open('config.yml', 'r') as config_yml_file:
  9 |     config = yaml.safe_load(config_yml_file)
 10 | 
 11 | 
 12 | def filterTags(tags):
 13 |     if tags is None:
 14 |         return
 15 |     newtags = {
 16 |         "level6_name": tags["level6name"],
 17 |         "level6_id": tags["level6id"],
 18 |         "level7_name": tags["level7name"],
 19 |         "level7_id": tags["level7id"],
 20 |         "level8_name": tags["level8name"],
 21 |         "level8_id": tags["level8id"],
 22 |         "level9_name": tags["level9name"],
 23 |         "level9_id": tags["level9id"],
 24 |         "boundary": "administrative"
 25 |     }
 26 | 
 27 |     if tags["level9name"] is None or tags["level9name"] == '':
 28 |         if tags["level8name"] is None or tags["level8name"] == '':
 29 |             if tags["level7name"] is None or tags["level7name"] == '':
 30 |                 if tags["level6name"] is None or tags["level6name"] == '':
 31 |                     newtags['name'] = ''
 32 |                 else:
 33 |                     newtags['name'] = tags['level6name']
 34 |             else:
 35 |                 newtags['name'] = tags['level7name']
 36 |         else:
 37 |             newtags['name'] = tags['level8name']
 38 |     else:
 39 |         newtags['name'] = tags['level9name']
 40 |         newtags["admin_level"] = "9"
 41 |     newtags["type"] = "boundary"
 42 |     newtags["source"] = config['changeset_source']
 43 |     return newtags
 44 | 
 45 | 
 46 | def splitWay(way, corners, features_map):
 47 |     idxs = [i for i, c in enumerate(way.points) if c in corners]
 48 |     splitends = 0 in idxs or (len(way.points) - 1) in idxs
 49 |     new_points = list()
 50 |     left = 0
 51 |     for cut in idxs:
 52 |         if cut != 0:
 53 |             new_points.append(way.points[left:(cut + 1)])
 54 |         left = cut
 55 |     # remainder
 56 |     if left < len(way.points) - 1:
 57 |         # closed way
 58 |         if not splitends and isClosed(way):
 59 |             new_points[0] = way.points[left:-1] + new_points[0]
 60 |         else:
 61 |             new_points.append(way.points[left:])
 62 |     # ~ print(len(way.points),[len(p) for p in new_points])
 63 | 
 64 |     new_ways = [way, ] + [geom.Way() for i in range(len(new_points) - 1)]
 65 | 
 66 |     if way in features_map:
 67 |         way_tags = features_map[way].tags
 68 | 
 69 |         for new_way in new_ways:
 70 |             if new_way != way:
 71 |                 feat = geom.Feature()
 72 |                 feat.geometry = new_way
 73 |                 feat.tags = way_tags
 74 |                 new_way.addparent(feat)
 75 | 
 76 |     for new_way, points in zip(new_ways, new_points):
 77 |         new_way.points = points
 78 |         if new_way.id != way.id:
 79 |             for point in points:
 80 |                 point.removeparent(way, shoulddestroy=False)
 81 |                 point.addparent(new_way)
 82 |     return new_ways
 83 | 
 84 | 
 85 | def mergeIntoNewRelation(way_parts):
 86 |     new_relation = geom.Relation()
 87 |     feat = geom.Feature()
 88 |     feat.geometry = new_relation
 89 |     new_relation.members = [(way, "outer") for way in way_parts]
 90 |     for way in way_parts:
 91 |         way.addparent(new_relation)
 92 |     return feat
 93 | 
 94 | 
 95 | def splitWayInRelation(rel, way_parts):
 96 |     way_roles = [m[1] for m in rel.members if m[0] == way_parts[0]]
 97 |     way_role = "" if len(way_roles) == 0 else way_roles[0]
 98 |     for way in way_parts[1:]:
 99 |         way.addparent(rel)
100 |         rel.members.append((way, way_role))
101 | 
102 | 
103 | def findSharedVertices(geometries):
104 |     points = [g for g in geometries if isinstance(g, geom.Point)]
105 |     vertices = list()
106 |     for p in points:
107 |         neighbors = set()
108 |         for way in p.parents:
109 |             for idx in findAll(way, p):
110 |                 for step in [-1, 1]:
111 |                     pt = way.points[(idx + step) % len(way.points)]
112 |                     if pt != p:
113 |                         neighbors.add(pt)
114 |         if len(neighbors) > 2:
115 |             vertices.append(p)
116 |     return vertices
117 | 
118 | 
119 | def findSelfIntersections(way):
120 |     intersections = list()
121 |     seen = set()
122 |     points = way.points
123 |     if isClosed(way):
124 |         points = points[:-1]
125 |     for point in points:
126 |         if point in seen:
127 |             intersections.append(point)
128 |         seen.add(point)
129 |     return intersections
130 | 
131 | 
132 | def similar(way1, way2):
133 |     if len(way1.points) != len(way2.points):
134 |         return False
135 |     w1 = [w.id for w in way1.points]
136 |     w2 = [w.id for w in way2.points]
137 |     if w1[0] not in w2:
138 |         return False
139 |     if set(w1) != set(w2):
140 |         return False
141 |     # closed way
142 |     if w1[0] == w1[-1]:
143 |         idx1 = w1.index(min(w1))
144 |         w1 = w1[idx1:-1] + w1[:idx1]
145 |         if w2[0] == w2[-1]:
146 |             idx2 = w2.index(min(w2))
147 |             w2 = w2[idx2:-1] + w2[:idx2]
148 |         # second way is not closed
149 |         else:
150 |             return False
151 |         if w1 == w2:
152 |             return True
153 |         if w1 == w2[:1] + w2[1:][::-1]:
154 |             return True
155 |     else:
156 |         if w1 == w2:
157 |             return True
158 |         if w1 == w2[::-1]:
159 |             return True
160 |     return False
161 | 
162 | 
163 | def isClosed(way):
164 |     return way.points[0] == way.points[-1]
165 | 
166 | 
167 | def findAll(way, node, start=0):
168 |     i = start - 1
169 |     while True:
170 |         try:
171 |             i = way.points.index(node, i + 1)
172 |             yield i
173 |         except ValueError:
174 |             break
175 | 
176 | 
177 | def preOutputTransform(geometries, features):
178 |     if geometries is None and features is None:
179 |         return
180 |     lint(geometries, features, "At entry", True)
181 |     print("Patching features")
182 |     for f in features:
183 |         if f not in f.geometry.parents:
184 |             f.geometry.addparent(f)
185 |     lint(geometries, features, "After parent fix", True)
186 |     print("Moving tags to relations")
187 |     # move tags, remove member ways as Features.
188 |     rels = [g for g in geometries if isinstance(g, geom.Relation)]
189 |     featuresmap = {feature.geometry: feature for feature in features}
190 |     for rel in rels:
191 |         relfeat = featuresmap[rel]
192 |         # splitWayInRelation does not add the relation as a parent.
193 |         for member, role in rel.members:
194 |             if rel not in member.parents:
195 |                 member.addparent(rel)
196 |         if relfeat.tags == {}:
197 |             outers = [m[0] for m in rel.members if m[1] == "outer"]
198 |             relfeat.tags.update(featuresmap[outers[0]].tags)
199 |             for member, role in rel.members:
200 |                 if member in featuresmap:
201 |                     memberfeature = featuresmap[member]
202 |                     del featuresmap[member]
203 |                     member.removeparent(memberfeature)
204 |                     features.remove(memberfeature)
205 |         else:
206 |             pass
207 |             # ~ print("Relation {} has tags.".format(rel.id),relfeat.tags)
208 |     # create relations for ways that are features.
209 |     ways = [g for g in geometries if isinstance(g, geom.Way)]
210 |     for way in ways:
211 |         if way in featuresmap:
212 |             feature = featuresmap[way]
213 |             newrel = geom.Relation()
214 |             way.addparent(newrel)
215 |             newrel.members.append((way, "outer"))
216 |             feature.replacejwithi(newrel, way)
217 |             featuresmap[newrel] = feature
218 |             del featuresmap[way]
219 |     lint(geometries, features, "Before split")
220 |     print("Finding shared vertices")
221 |     corners = set(findSharedVertices(geometries))
222 |     print("Splitting ways")
223 |     for way in ways:
224 |         is_way_in_relation = len([p for p in way.parents if isinstance(p, geom.Relation)]) > 0
225 |         thesecorners = corners.intersection(way.points)
226 |         # ~ if intersections:
227 |         # ~ print(len(intersections))
228 |         if len(thesecorners) > 0:
229 |             way_parts = splitWay(way, thesecorners, featuresmap)
230 |             if not is_way_in_relation:
231 |                 rel = mergeIntoNewRelation(way_parts)
232 |                 featuresmap[rel.geometry] = rel
233 |                 if way in featuresmap:
234 |                     rel.tags.update(featuresmap[way].tags)
235 |                 for wg, role in rel.geometry.members:
236 |                     if wg in featuresmap:
237 |                         wg.removeparent(featuresmap[wg])
238 |             else:
239 |                 for parent in way.parents:
240 |                     if isinstance(parent, geom.Relation):
241 |                         splitWayInRelation(parent, way_parts)
242 |     lint(geometries, features, "After split")
243 |     print("Merging relations")
244 |     worklist = sorted([g for g in geometries if isinstance(g, geom.Way)], key=lambda g: len(g.points))
245 |     # combine duplicate ways.
246 |     removed = list()
247 |     comparisons = 0
248 |     for i, way in enumerate(list(worklist)):
249 |         if i % 1000 == 0: print(i, len(list(worklist)))
250 |         # skip ways that are already gone
251 |         worklist.remove(way)
252 |         if way in removed:
253 |             continue
254 |         for otherway in worklist:
255 |             if len(otherway.points) > len(way.points):
256 |                 break
257 |             comparisons += 1
258 |             if similar(way, otherway):
259 |                 for parent in list(otherway.parents):
260 |                     if isinstance(parent, geom.Relation):
261 |                         parent.replacejwithi(way, otherway)
262 |                 removed.append(otherway)
263 |     print("Comparisons:", comparisons)
264 |     # ~ # results in duplicates
265 |     # ~ worklist = [g for g in geometries if isinstance(g, geom.Way)]
266 |     # ~ for way in worklist:
267 |     # ~ # similar ways must share first point
268 |     # ~ for otherway in way.points[0].parents:
269 |     # ~ # skip self and ways that are already merged
270 |     # ~ if otherway==way or way in removed:
271 |     # ~ continue
272 |     # ~ \            if similar(way,otherway):
273 |     # ~ for parent in list(otherway.parents):
274 |     # ~ if isinstance(parent, geom.Relation):
275 |     # ~ parent.replacejwithi(way, otherway)
276 |     # ~ removed.append(otherway)
277 | 
278 |     # merge adjacent ways
279 |     # ~ ways = [g for g in geometries if isinstance(g, geom.Way)]
280 |     # ~ junctions=set()
281 |     # ~ for way in ways:
282 |     # ~ for point in [way.points[0],way.points[-1]]:
283 |     # ~ if len(point.parents) == 2:
284 |     # ~ junctions.add(point)
285 |     # ~ print(len(junctions))
286 |     # ~ c=0
287 |     # ~ for j in junctions:
288 |     # ~ for p in j.parents:
289 |     # ~ for p2 in p.parents:
290 |     # ~ for p3 in p2.parents:
291 |     # ~ print(j.id,p3.tags["name"],len(p.points))
292 |     # ~ if c==10:
293 |     # ~ break
294 |     # ~ c+=1
295 |     # add tags to all ways
296 |     print("Tagging member ways")
297 |     ways = [g for g in geometries if isinstance(g, geom.Way)]
298 |     featuresmap = {feature.geometry: feature for feature in features}
299 |     for way in ways:
300 |         level9ids = []
301 |         for parent in way.parents:
302 |             admin_levels = []
303 |             boundaries = []
304 |             if parent in featuresmap:
305 |                 parfeat = featuresmap[parent]
306 |                 if "admin_level" in parfeat.tags:
307 |                     admin_levels.append(parfeat.tags["admin_level"])
308 |                 if "boundary" in parfeat.tags:
309 |                     boundaries.append(parfeat.tags["boundary"])
310 |                     level9ids.append(parfeat.tags['level9_id'])
311 |         newtags = {}
312 |         if admin_levels:
313 |             newtags["admin_level"] = min(admin_levels, key=int)
314 |         if boundaries:
315 |             newtags["boundary"] = boundaries.pop()
316 |         newtags['level9_id'] = ','.join(level9ids)
317 |         if newtags:
318 |             if way not in featuresmap:
319 |                 feat = geom.Feature()
320 |                 feat.geometry = way
321 |                 way.addparent(feat)
322 |             else:
323 |                 feat = featuresmap[way]
324 |             feat.tags.update(newtags)
325 |     lint(geometries, features, "After combine.")
326 |     for feat in features:
327 |         if isinstance(feat.geometry, geom.Relation):
328 |             feat.tags["type"] = "boundary"
329 | 
330 | 
331 | def lint(geometries, features, message="", blat=False):
332 |     if False:
333 |         return
334 |     ways = [g for g in geometries if isinstance(g, geom.Way)]
335 |     rels = [g for g in geometries if isinstance(g, geom.Relation)]
336 |     results = list()
337 |     # check for geometries with no parents.
338 |     noparents = list()
339 |     results.append(("{} geometries with no parents.", noparents))
340 |     for geo in geometries:
341 |         if len(geo.parents) == 0:
342 |             noparents.append(geo)
343 |     # check for features not listed as parents
344 |     notlisted = list()
345 |     results.append(("{} features not used as parents.", notlisted))
346 |     for f in features:
347 |         if f not in f.geometry.parents:
348 |             notlisted.append(f)
349 |     # check for duplicate nodes in ways
350 |     dupenodes = list()
351 |     results.append(("{} duplicate nodes in ways.", dupenodes))
352 |     onenodeways = list()
353 |     results.append(("{} one node ways.", onenodeways))
354 |     count = 0
355 |     for way in ways:
356 |         for i in range(1, len(way.points)):
357 |             if way.points[i - 1] == way.points[i]:
358 |                 dupenodes.append(way, i)
359 |                 count += 1
360 |         if len(way.points) == 1:
361 |             onenodeways.append(way)
362 |             count += 1
363 |     if message and any(result[1] for result in results):
364 |         print(message)
365 |     for msg, result in results:
366 |         if result:
367 |             print(msg.format(len(result)))
368 |             if blat:
369 |                 for p in result:
370 |                     print(p)
371 | 


--------------------------------------------------------------------------------
/conflate.py:
--------------------------------------------------------------------------------
  1 | import math
  2 | import os
  3 | import pickle
  4 | import sys
  5 | import time
  6 | import xml.etree.ElementTree as ET
  7 | from pathlib import Path
  8 | 
  9 | import matplotlib.pyplot as plt
 10 | import overpy
 11 | import pyproj
 12 | import shapely.geometry as geometry
 13 | import yaml
 14 | from osmapi import OsmApi
 15 | from shapely.ops import linemerge
 16 | 
 17 | from atomic_write import atomic_write
 18 | from common import retry_on_error
 19 | from processing_state import ProcessingState
 20 | 
 21 | 
 22 | def load_osm(path):
 23 |     nodes = {}
 24 |     ways = {}
 25 |     relations = {}
 26 |     root = ET.parse(path).getroot()
 27 |     for node in root.findall('node'):
 28 |         nodes[int(node.attrib['id'])] = {
 29 |             'lat': float(node.attrib['lat']),
 30 |             'lon': float(node.attrib['lon'])
 31 |         }
 32 | 
 33 |     for way in root.findall('way'):
 34 |         way_nodes = []
 35 |         for child in way.iter('nd'):
 36 |             way_nodes.append(int(child.attrib['ref']))
 37 |         ways[int(way.attrib['id'])] = {
 38 |             'nodes': way_nodes,
 39 |             'relations': '',
 40 |             'processed': ProcessingState.NO,
 41 |             'error_context': None,
 42 |             'osm_way': None
 43 |         }
 44 | 
 45 |     for relation in root.findall('relation'):
 46 |         relation_ways = []
 47 |         for child in relation.iter('member'):
 48 |             relation_ways.append(
 49 |                 {
 50 |                     'ref': int(child.attrib['ref']),
 51 |                     'role': child.attrib['role'],
 52 |                     'type': child.attrib['type']
 53 |                 })
 54 |         tags = {}
 55 |         for child in relation.iter('tag'):
 56 |             tags[child.attrib['k']] = child.attrib['v']
 57 |         relations[int(relation.attrib['id'])] = {
 58 |             'ways': relation_ways,
 59 |             'tags': tags
 60 |         }
 61 | 
 62 |     return {'relations': relations, 'ways': ways, 'nodes': nodes}
 63 | 
 64 | 
 65 | @retry_on_error()
 66 | def get_osm_shared_ways(api, r1, r2, country, id_key):
 67 |     response = api.query(f"""
 68 |         area["name"="{country}"]["admin_level"=2]->.a;
 69 |         relation(area.a)["boundary"="administrative"]["admin_level"=9]["{id_key}"="{r1}"]->.firstRelation;
 70 |         relation(area.a)["boundary"="administrative"]["admin_level"=9]["{id_key}"="{r2}"]->.secondRelation;
 71 |         (.firstRelation;>;)->.a1;
 72 |         (.secondRelation;>;)->.a2;
 73 |         (.a1;- .a2;)->.a3;
 74 |         (.a1;- .a3;)->.a4;
 75 |         way.a4;
 76 |         (._;>;);
 77 |         out;
 78 |         // &contact=https://github.com/stalker314314/osm-admin-boundary-conflation/
 79 |     """)
 80 |     return response
 81 | 
 82 | 
 83 | @retry_on_error()
 84 | def get_osm_single_way(api, r1, country, id_key):
 85 |     response = api.query(f"""
 86 |         area["name"="{country}"]["admin_level"=2]->.a;
 87 |         relation(area.a)["boundary"="administrative"]["admin_level"=9]["{id_key}"="{r1}"]->.firstRelation;
 88 |         relation(area.a)["boundary"="administrative"]["admin_level"=9]["{id_key}"!="{r1}"]->.secondRelation;
 89 |         (.firstRelation ;>;) -> .a1;
 90 |         (.secondRelation;>;) -> .a2;
 91 |         (way.a1;- way.a2;) -> .a3;
 92 |         way.a3;
 93 |         (._;>;);
 94 |         out;
 95 |         // &contact=https://github.com/stalker314314/osm-admin-boundary-conflation/
 96 |     """)
 97 |     return response
 98 | 
 99 | 
100 | @retry_on_error()
101 | def get_entities_shared_with_way(api, way_id):
102 |     response = api.query("""
103 |         way({0});
104 |         ._;>;
105 |         ._;<;
106 |         out;
107 |         // &contact=https://github.com/stalker314314/osm-admin-boundary-conflation/
108 |         """.format(way_id))
109 |     return response
110 | 
111 | 
112 | def create_geometry_from_osm_way(way):
113 |     # Try to build shapely polygon out of this data
114 |     lss = []
115 |     ls_coords = []
116 |     for node in way.nodes:
117 |         ls_coords.append((node.lon, node.lat))
118 |     lss.append(geometry.LineString(ls_coords))
119 | 
120 |     merged = linemerge([*lss])
121 |     return merged
122 | 
123 | 
124 | def create_geometry_from_osm_file_data(source_data, way):
125 |     # Try to build shapely polygon out of .osm data
126 |     lss = []
127 |     ls_coords = []
128 |     for node_id in way['nodes']:
129 |         node = source_data['nodes'][node_id]
130 |         ls_coords.append((node['lon'], node['lat']))
131 |     lss.append(geometry.LineString(ls_coords))
132 | 
133 |     merged = linemerge([*lss])
134 |     return merged
135 | 
136 | 
137 | def unglue_ways(config, osmapi, way_boundary_id, way_other_id):
138 |     """
139 |     Given admin boundary way and other way that shares some nodes with it, unglues those shared nodes into separate ones
140 |     It adds new node and changes boundary to remove shared one and adds new one at the same place.
141 |     It will not unglue endpoints
142 |     """
143 |     auto_proceed = config['auto_proceed']
144 | 
145 |     way_boundary = osmapi.WayGet(way_boundary_id)
146 |     way_other = osmapi.WayGet(way_other_id)
147 |     if len(way_other['tag']) == 0 or len(way_boundary['tag']) == 0:
148 |         print('One of glued ways do not have any tag. This might be boundary in disguise, skipping')
149 |         return False
150 |     shared_nodes = set(way_boundary['nd']) & set(way_other['nd'])
151 |     before_removing_endpoints = len(shared_nodes)
152 |     if way_boundary['nd'][0] in shared_nodes:
153 |         shared_nodes.remove(way_boundary['nd'][0])
154 |     if way_boundary['nd'][-1] in shared_nodes:
155 |         shared_nodes.remove(way_boundary['nd'][-1])
156 | 
157 |     if len(shared_nodes) == 0:
158 |         if before_removing_endpoints > 0:
159 |             print('There are glued nodes, but they are endpoints and script will not unglue them')
160 |         return False
161 | 
162 |     print('{0} nodes will be unglued from boundary https://www.openstreetmap.org/way/{1} and way '
163 |           'https://www.openstreetmap.org/way/{2}'.format(len(shared_nodes), way_boundary_id, way_other_id))
164 |     if len(shared_nodes) > 0 and not auto_proceed:
165 |         proceed = input('Proceed (Y/n)')
166 |         if not (proceed == '' or proceed.lower() == 'y' or proceed.lower() == u'з'):
167 |             return False
168 | 
169 |     done_any = False
170 |     i = 1
171 |     for shared_node in shared_nodes:
172 |         node = osmapi.NodeGet(shared_node)
173 |         if len(node['tag']) > 0:
174 |             print('Node to be unglued has tags, skipping')
175 |             continue
176 |         added_node = {'id': -i, 'lon': node['lon'], 'lat': node['lat'], 'tag': {}}
177 |         i = i + 1
178 |         osmapi.NodeCreate(added_node)
179 |         index = way_boundary['nd'].index(shared_node)
180 |         del way_boundary['nd'][index]
181 |         way_boundary['nd'].insert(index, added_node['id'])
182 |         done_any = True
183 |     if done_any:
184 |         osmapi.WayUpdate(way_boundary)
185 |         osmapi.flush()
186 |         return True
187 |     else:
188 |         return False
189 | 
190 | 
191 | def is_conflate_possible(config, osmapi, overpass_api, shapely_source_way, found_osm_way, shapely_found_osm_way):
192 |     # Check if source or targets are not huge (we need this as we want to put conflation of way in a single changeset)
193 |     assert len(shapely_source_way.coords) < 3000
194 |     assert len(shapely_found_osm_way.coords) < 2000
195 | 
196 |     unglue_ways_as_needed = config['unglue_ways_as_needed']
197 |     max_distance_end_points_to_consider_in_meters = config['max_distance_end_points_to_consider_in_meters']
198 | 
199 |     # Check if way is not national border
200 |     if 'admin_level' in found_osm_way.tags and int(found_osm_way.tags['admin_level']) <= 2:
201 |         print('Shared way is national border, skipping')
202 |         return ProcessingState.ERROR_NATIONAL_BORDER, None
203 | 
204 |     # Check if way in OSM do not have any tags
205 |     for tag in found_osm_way.tags:
206 |         if tag in ('admin_level', 'boundary', 'note', 'source', 'fixme', 'type', 'int_name'):
207 |             continue
208 |         if tag.startswith('name'):
209 |             continue
210 |         print('Found unexpected tag {0} in way to conflate, skipping'.format(tag))
211 |         return ProcessingState.ERROR_UNEXPECTED_TAG, tag
212 | 
213 |     # Check if nodes in way don't belong to any other way or relation
214 |     response = get_entities_shared_with_way(overpass_api, found_osm_way.id)
215 |     for way in response.ways:
216 |         if 'admin_level' in way.tags and int(way.tags['admin_level']) <= 2:
217 |             print(f'Way to conflate contains node which is also part of way https://www.openstreetmap.org/way/{way.id} which is national border, skipping')
218 |             return ProcessingState.ERROR_NODE_IN_NATIONAL_BORDER, str(way.id)
219 |         if 'boundary' not in way.tags:
220 |             print(f'Way to conflate contains node which is also part of way https://www.openstreetmap.org/way/{way.id} which do not have boundary tag, skipping')
221 |             if unglue_ways_as_needed:
222 |                 one_way = unglue_ways(config, osmapi, found_osm_way.id, way.id)
223 |                 if not one_way:
224 |                     other_way = unglue_ways(config, osmapi, way.id, found_osm_way.id)
225 |                     if not other_way:
226 |                         return ProcessingState.ERROR_NODE_IN_OTHER_WAYS, str(way.id)
227 |             else:
228 |                 return ProcessingState.ERROR_NODE_IN_OTHER_WAYS, str(way.id)
229 |         elif way.tags['boundary'] != 'administrative':
230 |             print(f'Way to conflate contains node which is also part of way https://www.openstreetmap.org/way/{way.id} which boundary tag != administrative, skipping')
231 |             if unglue_ways_as_needed:
232 |                 one_way = unglue_ways(config, osmapi, found_osm_way.id, way.id)
233 |                 if not one_way:
234 |                     other_way = unglue_ways(config, osmapi, way.id, found_osm_way.id)
235 |                     if not other_way:
236 |                         return ProcessingState.ERROR_NODE_IN_OTHER_WAYS, str(way.id)
237 |             else:
238 |                 return ProcessingState.ERROR_NODE_IN_OTHER_WAYS, str(way.id)
239 |     for relation in response.relations:
240 |         is_city = 'place' in relation.tags and relation.tags['place'] == 'city'
241 |         if 'admin_level' not in relation.tags:
242 |             if not is_city:
243 |                 print(f'Way to conflate belongs to relation https://www.openstreetmap.org/relation/{relation.id} which do not have admin_level tag, skipping')
244 |                 return ProcessingState.ERROR_NODE_IN_OTHER_RELATION, str(relation.id)
245 |         elif int(relation.tags['admin_level']) <= 2:
246 |             print(f'Way to conflate belongs to relation https://www.openstreetmap.org/relation/{relation.id} which is national border, skipping')
247 |             return ProcessingState.ERROR_NODE_IN_NATIONAL_RELATION, str(relation.id)
248 |         if 'type' not in relation.tags:
249 |             print(f'Way to conflate belongs to relation https://www.openstreetmap.org/relation/{relation.id} which do not have type tag, skipping')
250 |             return ProcessingState.ERROR_NODE_IN_OTHER_RELATION, str(relation.id)
251 |         elif relation.tags['type'] != 'boundary' and not is_city:
252 |             print(f'Way to conflate belongs to relation https://www.openstreetmap.org/relation/{relation.id} where type != boundary, skipping')
253 |             return ProcessingState.ERROR_NODE_IN_OTHER_RELATION, str(relation.id)
254 |         if 'boundary' not in relation.tags:
255 |             if not is_city:
256 |                 print(f'Way to conflate belongs to relation https://www.openstreetmap.org/relation/{relation.id} which do not have boundary tag, skipping')
257 |                 return ProcessingState.ERROR_NODE_IN_OTHER_RELATION, str(relation.id)
258 |         elif relation.tags['boundary'] != 'administrative' and relation.tags['boundary'] != 'census':
259 |             print(f'Way to conflate belongs to relation https://www.openstreetmap.org/relation/{relation.id} where boundary != administrative or census, skipping')
260 |             return ProcessingState.ERROR_NODE_IN_OTHER_RELATION, str(relation.id)
261 | 
262 |     # Check if nodes on way in OSM are not having any tags
263 |     nodes_with_tags = [n for n in found_osm_way.nodes if len(n.tags) > 0 and not (len(n.tags) == 1 and 'created_by' in n.tags)]
264 |     if len(nodes_with_tags) > 0:
265 |         return ProcessingState.ERROR_NODES_WITH_TAGS, ','.join([str(n.id) for n in nodes_with_tags])
266 | 
267 |     # Check if end points are close enough
268 |     distance, should_reverse = get_bigger_endpoint_difference(shapely_source_way, shapely_found_osm_way)
269 |     if distance > max_distance_end_points_to_consider_in_meters:
270 |         print(f'End points of ways to conflate are different for more that {max_distance_end_points_to_consider_in_meters}m ({distance}m), skipping')
271 |         return ProcessingState.ERROR_END_POINTS_FAR_APART, str(distance)
272 |     if should_reverse:
273 |         shapely_source_way.coords = list(shapely_source_way.coords[::-1])
274 | 
275 |     return ProcessingState.CHECKED_POSSIBLE, None
276 | 
277 | 
278 | def get_bigger_endpoint_difference(shapely_source_way, shapely_found_osm_way):
279 |     should_reverse = False
280 |     geod = pyproj.Geod(ellps='WGS84')
281 |     _, _, distance11 = geod.inv(shapely_found_osm_way.coords[0][0], shapely_found_osm_way.coords[0][1],
282 |                               shapely_source_way.coords[0][0], shapely_source_way.coords[0][1])
283 |     _, _, distance12 = geod.inv(shapely_found_osm_way.coords[0][0], shapely_found_osm_way.coords[0][1],
284 |                               shapely_source_way.coords[-1][0], shapely_source_way.coords[-1][1])
285 |     if distance12 < distance11:
286 |         should_reverse = True
287 |     distance1 = min(distance11, distance12)
288 |     if should_reverse:
289 |         _, _, distance2 = geod.inv(shapely_found_osm_way.coords[-1][0], shapely_found_osm_way.coords[-1][1],
290 |                                    shapely_source_way.coords[0][0], shapely_source_way.coords[0][1])
291 |     else:
292 |         _, _, distance2 = geod.inv(shapely_found_osm_way.coords[-1][0], shapely_found_osm_way.coords[-1][1],
293 |                                    shapely_source_way.coords[-1][0], shapely_source_way.coords[-1][1])
294 |     return max(distance1, distance2), should_reverse
295 | 
296 | 
297 | def is_same_geometry(shapely_source_way, shapely_found_osm_way):
298 |     if shapely_source_way.is_closed != shapely_found_osm_way.is_closed:
299 |         return False
300 |     if shapely_source_way.is_ring != shapely_found_osm_way.is_ring:
301 |         return False
302 |     if len(shapely_source_way.coords) != len(shapely_found_osm_way.coords):
303 |         return False
304 |     # Check distance of endpoints and figure out if ways should be reversed
305 |     distance, should_reverse = get_bigger_endpoint_difference(shapely_source_way, shapely_found_osm_way)
306 |     if distance > 1:
307 |         return False
308 |     if should_reverse:
309 |         shapely_source_way.coords = list(shapely_source_way.coords[::-1])
310 |     # Go for each node and check distance
311 |     geod = pyproj.Geod(ellps='WGS84')
312 |     for p1, p2 in zip(shapely_source_way.coords, shapely_found_osm_way.coords):
313 |         _, _, distance = geod.inv(p1[0], p1[1], p2[0], p2[1])
314 |         if distance > 1:
315 |             return False
316 |     return True
317 | 
318 | 
319 | def calculate_initial_compass_bearing(pointA, pointB):
320 |     """
321 |     Calculates the bearing between two points.
322 |     The formulae used is the following:
323 |         θ = atan2(sin(Δlong).cos(lat2),
324 |                   cos(lat1).sin(lat2) − sin(lat1).cos(lat2).cos(Δlong))
325 |     :Parameters:
326 |       - `pointA: The tuple representing the latitude/longitude for the
327 |         first point. Latitude and longitude must be in decimal degrees
328 |       - `pointB: The tuple representing the latitude/longitude for the
329 |         second point. Latitude and longitude must be in decimal degrees
330 |     :Returns:
331 |       The bearing in degrees
332 |     :Returns Type:
333 |       float
334 |     """
335 |     if (type(pointA) != tuple) or (type(pointB) != tuple):
336 |         raise TypeError("Only tuples are supported as arguments")
337 | 
338 |     lat1 = math.radians(pointA[0])
339 |     lat2 = math.radians(pointB[0])
340 | 
341 |     diffLong = math.radians(pointB[1] - pointA[1])
342 | 
343 |     x = math.sin(diffLong) * math.cos(lat2)
344 |     y = math.cos(lat1) * math.sin(lat2) - (math.sin(lat1)
345 |             * math.cos(lat2) * math.cos(diffLong))
346 | 
347 |     initial_bearing = math.atan2(x, y)
348 | 
349 |     # Now we have the initial bearing but math.atan2 return values
350 |     # from -180° to + 180° which is not what we want for a compass bearing
351 |     # The solution is to normalize the initial bearing as shown below
352 |     initial_bearing = math.degrees(initial_bearing)
353 |     compass_bearing = (initial_bearing + 360) % 360
354 | 
355 |     return compass_bearing
356 | 
357 | 
358 | def conflate_way(config, osmapi, overpass_api, source_data, source_way, found_osm_way):
359 |     auto_proceed = config['auto_proceed']
360 |     dry_run = config['dry_run']
361 | 
362 |     shapely_found_osm_way = create_geometry_from_osm_way(found_osm_way)
363 |     shapely_source_way = create_geometry_from_osm_file_data(source_data, source_way)
364 | 
365 |     if len(source_way['nodes']) >= 2000:
366 |         # OSM does not support this many nodes in way, human will need to simplify this
367 |         print('Way has too many nodes ({0}) and 2000 is allowed'.format(len(source_way['nodes'])))
368 |         return ProcessingState.ERROR_TOO_MANY_NODES, None
369 | 
370 |     if not shapely_found_osm_way.is_valid or not shapely_source_way.is_valid:
371 |         print('Shape is invalid, skipping')
372 |         return ProcessingState.ERROR_INVALID_SHAPE, None
373 |     if shapely_found_osm_way.is_closed or shapely_found_osm_way.is_ring or \
374 |             shapely_source_way.is_closed or shapely_source_way.is_ring:
375 |         print('Shape is closed loop, cannot handle it, skipping')
376 |         return ProcessingState.ERROR_CLOSED_SHAPE, None
377 | 
378 |     if is_same_geometry(shapely_source_way, shapely_found_osm_way):
379 |         print('Way to conflate seems already conflated, skipping')
380 |         return ProcessingState.CONFLATED, None
381 |     is_conflate_possible_error, error_context = is_conflate_possible(config, osmapi, overpass_api, shapely_source_way,
382 |                                                                      found_osm_way, shapely_found_osm_way)
383 |     if is_conflate_possible_error != ProcessingState.CHECKED_POSSIBLE:
384 |         return is_conflate_possible_error, error_context
385 | 
386 |     # Do basic check that can cut off lot of already-almost conflated ways
387 |     # Shapes are same if inflated way can fit inside other way and if angle (in degrees) of end points is less than 5 degree
388 |     almost_same_ways = shapely_source_way.within(shapely_found_osm_way.buffer(0.005))
389 |     angle1 = calculate_initial_compass_bearing(shapely_found_osm_way.coords[0], shapely_found_osm_way.coords[-1])
390 |     angle2 = calculate_initial_compass_bearing(shapely_source_way.coords[0], shapely_source_way.coords[-1])
391 |     heuristically_same = almost_same_ways and math.fabs(angle1-angle2) < 5
392 |     if not heuristically_same:
393 |         if not auto_proceed:
394 |             # # TODO: use something better, like https://stackoverflow.com/questions/56448933/plotting-shapely-polygon-on-cartopy
395 |             plt.figure()
396 |             plt.plot(*shapely_found_osm_way.coords.xy, color='red')
397 |             plt.plot(*shapely_source_way.coords.xy, color='green')
398 |             plt.show()
399 |             plt.pause(1)
400 | 
401 |             proceed = input('Does these shapes match? (Y/n)')
402 |             if not (proceed == '' or proceed.lower() == 'y' or proceed.lower() == u'з'):
403 |                 return ProcessingState.ERROR_GEOMETRY_WRONG, None
404 |     else:
405 |         print('Detected almost same ways, skipping human check')
406 | 
407 |     osm_way_nodes_to_conflate = osmapi.WayFull(found_osm_way.id)
408 |     osm_way_to_conflate = osmapi.WayGet(found_osm_way.id)
409 |     nodes_to_delete = []
410 |     assert len(osm_way_nodes_to_conflate) == len(osm_way_to_conflate['nd']) + 1
411 |     for i in range(len(osm_way_to_conflate['nd'])-1):
412 |         # since we are in-place modifying this list, we need to offset it by this much,
413 |         # this is why we substract len of nodes_to_delete
414 |         node_id_to_conflate = osm_way_to_conflate['nd'][i-len(nodes_to_delete)]
415 |         node_to_conflate = next(n['data'] for n in osm_way_nodes_to_conflate if n['data']['id'] == node_id_to_conflate)
416 |         if i < len(shapely_source_way.coords) - 1:
417 |             geod = pyproj.Geod(ellps='WGS84')
418 |             _, _, distance = geod.inv(node_to_conflate['lon'], node_to_conflate['lat'],
419 |                                       shapely_source_way.coords[i][0], shapely_source_way.coords[i][1])
420 |             node_to_conflate['lon'] = shapely_source_way.coords[i][0]
421 |             node_to_conflate['lat'] = shapely_source_way.coords[i][1]
422 |             if not dry_run:
423 |                 osmapi.NodeUpdate(node_to_conflate)
424 |         else:
425 |             nodes_to_delete.append(node_to_conflate)
426 |             osm_way_to_conflate['nd'].remove(node_to_conflate['id'])
427 |     for i in range(len(osm_way_to_conflate['nd'])-1, len(shapely_source_way.coords) - 1):
428 |         added_node = {'id': -i, 'lon': shapely_source_way.coords[i][0], 'lat': shapely_source_way.coords[i][1], 'tag': {}}
429 |         if not dry_run:
430 |             osmapi.NodeCreate(added_node)
431 |         osm_way_to_conflate['nd'].insert(-1, added_node['id'])
432 |     # Fix last node
433 |     last_node_id = osm_way_to_conflate['nd'][-1]
434 |     last_node_to_conflate = next(n['data'] for n in osm_way_nodes_to_conflate if n['data']['id'] == last_node_id)
435 |     _, _, distance = geod.inv(last_node_to_conflate['lon'], last_node_to_conflate['lat'],
436 |                               shapely_source_way.coords[-1][0], shapely_source_way.coords[-1][1])
437 | 
438 |     last_node_to_conflate['lon'] = shapely_source_way.coords[-1][0]
439 |     last_node_to_conflate['lat'] = shapely_source_way.coords[-1][1]
440 |     if not dry_run:
441 |         osmapi.NodeUpdate(last_node_to_conflate)
442 | 
443 |     if not dry_run:
444 |         osmapi.WayUpdate(osm_way_to_conflate)
445 |         # Deleting nodes needs to happen after we update way
446 |         for node_to_delete in nodes_to_delete:
447 |             osmapi.NodeDelete(node_to_delete)
448 |         osmapi.flush()
449 |         time.sleep(5)
450 |         return ProcessingState.CONFLATED, None
451 |     else:
452 |         return ProcessingState.CHECKED_POSSIBLE, None
453 | 
454 | 
455 | def main(input_osm_file, progress_file):
456 |     with open('config.yml', 'r') as config_yml_file:
457 |         config = yaml.safe_load(config_yml_file)
458 | 
459 |     overpass_api = overpy.Overpass(url=config['overpass_url'])
460 |     auto_proceed = config['auto_proceed']
461 |     country = config['country']
462 |     level9_ref_key = config['level9_ref_key']
463 | 
464 |     osmapi = OsmApi(passwordfile='osm-password',
465 |                     changesetauto=True,
466 |                     changesetautosize=10000, changesetautotags=
467 |                     {
468 |                         u"comment": config['changeset_comment'],
469 |                         u"tag": u"mechanical=yes", u"source": config['changeset_source']
470 |                     })
471 | 
472 |     if not os.path.isfile(progress_file):
473 |         print(f'Cannot find {progress_file}, starting from scratch')
474 |         source_data = load_osm(input_osm_file)
475 |         print(f'Loaded .osm file {input_osm_file}')
476 |         Path(progress_file).touch()  # need to touch file for atomic writes later
477 |     else:
478 |         with open(progress_file, 'rb') as p:
479 |             source_data = pickle.load(p)
480 | 
481 |     # Iterate for each way in .osm
482 |     count_processed = 0
483 |     for way_id, way in sorted(source_data['ways'].items(), key=lambda x: x[0], reverse=True):
484 |         count_processed = count_processed + 1
485 |         print('Processing {0}/{1}'.format(count_processed, len(source_data['ways'])))
486 |         if way['processed'] != ProcessingState.NO:
487 |             continue
488 |         # Find relations this way is part of
489 |         relations = []
490 |         for relation_id, relation in source_data['relations'].items():
491 |             ways = [w for w in relation['ways'] if w['ref'] == way_id]
492 |             assert len(ways) <= 1
493 |             if len(ways) == 1:
494 |                 relations.append(relation)
495 |         assert len(relations) > 0
496 |         if len(relations) == 2:
497 |             relation_text = "{0} (ref: {1}) - {2} (ref: {3})".format(
498 |                 relations[0]['tags']['name'], relations[0]['tags']['level9_id'],
499 |                 relations[1]['tags']['name'], relations[1]['tags']['level9_id'])
500 |         elif len(relations) == 1:
501 |             relation_text = "{0} (ref: {1})".format(
502 |                 relations[0]['tags']['name'], relations[0]['tags']['level9_id'])
503 |         elif len(relations) == 3:
504 |             relation_text = "{0} (ref: {1}) - {2} (ref: {3}) - {4} (ref: {5})".format(
505 |                 relations[0]['tags']['name'], relations[0]['tags']['level9_id'],
506 |                 relations[1]['tags']['name'], relations[1]['tags']['level9_id'],
507 |                 relations[2]['tags']['name'], relations[2]['tags']['level9_id'])
508 |         way['relations'] = relation_text
509 | 
510 |         # If way is shared between two relations, we try to find it in OSM using that information,
511 |         # Otherwise, if it is part of just one relation, we try to find it in OSM with that.
512 |         if len(relations) == 2:
513 |             settlement0_id = relations[0]['tags']['level9_id']
514 |             settlement1_id = relations[1]['tags']['level9_id']
515 |             osm_response = get_osm_shared_ways(overpass_api, settlement0_id, settlement1_id, country, level9_ref_key)
516 |             if len(osm_response.ways) == 0:
517 |                 print('Cannot find shared way in OSM between settlements {0} (ref: {1}) and {2} (ref: {3}), skipping'.
518 |                       format(relations[0]['tags']['name'], settlement0_id,
519 |                              relations[1]['tags']['name'], settlement1_id))
520 |                 way['processed'] = ProcessingState.ERROR_SHARED_WAY_NOT_FOUND
521 |                 way['error_context'] = None
522 |             elif len(osm_response.ways) > 1:
523 |                 print('More than 1 shared way in OSM between settlements {0} (ref: {1}) and {2} (ref: {3}), '
524 |                       'fix by merging ways manually, skipping'.
525 |                       format(relations[0]['tags']['name'], settlement0_id,
526 |                              relations[1]['tags']['name'], settlement1_id))
527 |                 way['processed'] = ProcessingState.ERROR_MULTIPLE_SHARED_WAYS
528 |                 way['error_context'] = ','.join([str(w.id) for w in osm_response.ways])
529 |             else:
530 |                 print('Processing way https://www.openstreetmap.org/way/{0} shared between {1} and {2}'.format(
531 |                     osm_response.ways[0].id, relations[0]['tags']['name'], relations[1]['tags']['name']))
532 |                 processed, error_context = conflate_way(config, osmapi, overpass_api, source_data, way, osm_response.ways[0])
533 |                 way['processed'] = processed
534 |                 way['osm_way'] = osm_response.ways[0].id
535 |                 way['error_context'] = error_context
536 |         elif len(relations) == 1:
537 |             settlement_id = relations[0]['tags']['level9_id']
538 |             osm_response = get_osm_single_way(overpass_api, settlement_id, country, level9_ref_key)
539 |             if len(osm_response.ways) == 0:
540 |                 print('Cannot find way in OSM that belongs only to settlement {0} (ref: {1}), skipping'.
541 |                       format(relations[0]['tags']['name'], settlement_id))
542 |                 way['processed'] = ProcessingState.ERROR_WAY_NOT_FOUND
543 |                 way['error_context'] = None
544 |             elif len(osm_response.ways) > 1:
545 |                 print('More than 1 way in OSM that belongs only to settlement {0} (ref: {1}), '
546 |                       'fix by merging ways manually, skipping'.format(
547 |                     relations[0]['tags']['name'], settlement_id))
548 |                 way['processed'] = ProcessingState.ERROR_MULTIPLE_SINGLE_WAY
549 |                 way['error_context'] = ','.join([str(w.id) for w in osm_response.ways])
550 |             else:
551 |                 print('Processing way https://www.openstreetmap.org/way/{0} belonging only to {1}'.format(
552 |                     osm_response.ways[0].id, relations[0]['tags']['name']))
553 |                 processed, error_context = conflate_way(config, osmapi, overpass_api, source_data, way, osm_response.ways[0])
554 |                 way['processed'] = processed
555 |                 way['osm_way'] = osm_response.ways[0].id
556 |                 way['error_context'] = error_context
557 |         elif len(relations) > 2:
558 |             way['processed'] = ProcessingState.ERROR_OVERLAPPING_WAYS
559 |             way['osm_way'] = None
560 |             way['error_context'] = None
561 | 
562 |         # Dump current progress (use atomic_writes to guard for semi-written files as those pickle dumps can be huge)
563 |         with atomic_write(progress_file, text=False, keep=False) as h:
564 |             pickle.dump(source_data, h, protocol=pickle.DEFAULT_PROTOCOL)
565 | 
566 |         if not auto_proceed:
567 |             proceed = input('Continue with next way? (Y/n)?')
568 |             if proceed == '' or proceed.lower() == 'y' or proceed.lower() == u'з':
569 |                 continue
570 |             break
571 |         else:
572 |             time.sleep(2)
573 | 
574 | 
575 | if __name__ == '__main__':
576 |     if len(sys.argv) != 3:
577 |         print("Usage: ./conflate.py <input_osm_file> <progress_file>")
578 |         exit()
579 |     input_osm_file = sys.argv[1]
580 |     progress_file = sys.argv[2]
581 |     main(input_osm_file, progress_file)
582 | 


--------------------------------------------------------------------------------
/LICENSE:
--------------------------------------------------------------------------------
  1 |                     GNU GENERAL PUBLIC LICENSE
  2 |                        Version 3, 29 June 2007
  3 | 
  4 |  Copyright (C) 2007 Free Software Foundation, Inc. <https://fsf.org/>
  5 |  Everyone is permitted to copy and distribute verbatim copies
  6 |  of this license document, but changing it is not allowed.
  7 | 
  8 |                             Preamble
  9 | 
 10 |   The GNU General Public License is a free, copyleft license for
 11 | software and other kinds of works.
 12 | 
 13 |   The licenses for most software and other practical works are designed
 14 | to take away your freedom to share and change the works.  By contrast,
 15 | the GNU General Public License is intended to guarantee your freedom to
 16 | share and change all versions of a program--to make sure it remains free
 17 | software for all its users.  We, the Free Software Foundation, use the
 18 | GNU General Public License for most of our software; it applies also to
 19 | any other work released this way by its authors.  You can apply it to
 20 | your programs, too.
 21 | 
 22 |   When we speak of free software, we are referring to freedom, not
 23 | price.  Our General Public Licenses are designed to make sure that you
 24 | have the freedom to distribute copies of free software (and charge for
 25 | them if you wish), that you receive source code or can get it if you
 26 | want it, that you can change the software or use pieces of it in new
 27 | free programs, and that you know you can do these things.
 28 | 
 29 |   To protect your rights, we need to prevent others from denying you
 30 | these rights or asking you to surrender the rights.  Therefore, you have
 31 | certain responsibilities if you distribute copies of the software, or if
 32 | you modify it: responsibilities to respect the freedom of others.
 33 | 
 34 |   For example, if you distribute copies of such a program, whether
 35 | gratis or for a fee, you must pass on to the recipients the same
 36 | freedoms that you received.  You must make sure that they, too, receive
 37 | or can get the source code.  And you must show them these terms so they
 38 | know their rights.
 39 | 
 40 |   Developers that use the GNU GPL protect your rights with two steps:
 41 | (1) assert copyright on the software, and (2) offer you this License
 42 | giving you legal permission to copy, distribute and/or modify it.
 43 | 
 44 |   For the developers' and authors' protection, the GPL clearly explains
 45 | that there is no warranty for this free software.  For both users' and
 46 | authors' sake, the GPL requires that modified versions be marked as
 47 | changed, so that their problems will not be attributed erroneously to
 48 | authors of previous versions.
 49 | 
 50 |   Some devices are designed to deny users access to install or run
 51 | modified versions of the software inside them, although the manufacturer
 52 | can do so.  This is fundamentally incompatible with the aim of
 53 | protecting users' freedom to change the software.  The systematic
 54 | pattern of such abuse occurs in the area of products for individuals to
 55 | use, which is precisely where it is most unacceptable.  Therefore, we
 56 | have designed this version of the GPL to prohibit the practice for those
 57 | products.  If such problems arise substantially in other domains, we
 58 | stand ready to extend this provision to those domains in future versions
 59 | of the GPL, as needed to protect the freedom of users.
 60 | 
 61 |   Finally, every program is threatened constantly by software patents.
 62 | States should not allow patents to restrict development and use of
 63 | software on general-purpose computers, but in those that do, we wish to
 64 | avoid the special danger that patents applied to a free program could
 65 | make it effectively proprietary.  To prevent this, the GPL assures that
 66 | patents cannot be used to render the program non-free.
 67 | 
 68 |   The precise terms and conditions for copying, distribution and
 69 | modification follow.
 70 | 
 71 |                        TERMS AND CONDITIONS
 72 | 
 73 |   0. Definitions.
 74 | 
 75 |   "This License" refers to version 3 of the GNU General Public License.
 76 | 
 77 |   "Copyright" also means copyright-like laws that apply to other kinds of
 78 | works, such as semiconductor masks.
 79 | 
 80 |   "The Program" refers to any copyrightable work licensed under this
 81 | License.  Each licensee is addressed as "you".  "Licensees" and
 82 | "recipients" may be individuals or organizations.
 83 | 
 84 |   To "modify" a work means to copy from or adapt all or part of the work
 85 | in a fashion requiring copyright permission, other than the making of an
 86 | exact copy.  The resulting work is called a "modified version" of the
 87 | earlier work or a work "based on" the earlier work.
 88 | 
 89 |   A "covered work" means either the unmodified Program or a work based
 90 | on the Program.
 91 | 
 92 |   To "propagate" a work means to do anything with it that, without
 93 | permission, would make you directly or secondarily liable for
 94 | infringement under applicable copyright law, except executing it on a
 95 | computer or modifying a private copy.  Propagation includes copying,
 96 | distribution (with or without modification), making available to the
 97 | public, and in some countries other activities as well.
 98 | 
 99 |   To "convey" a work means any kind of propagation that enables other
100 | parties to make or receive copies.  Mere interaction with a user through
101 | a computer network, with no transfer of a copy, is not conveying.
102 | 
103 |   An interactive user interface displays "Appropriate Legal Notices"
104 | to the extent that it includes a convenient and prominently visible
105 | feature that (1) displays an appropriate copyright notice, and (2)
106 | tells the user that there is no warranty for the work (except to the
107 | extent that warranties are provided), that licensees may convey the
108 | work under this License, and how to view a copy of this License.  If
109 | the interface presents a list of user commands or options, such as a
110 | menu, a prominent item in the list meets this criterion.
111 | 
112 |   1. Source Code.
113 | 
114 |   The "source code" for a work means the preferred form of the work
115 | for making modifications to it.  "Object code" means any non-source
116 | form of a work.
117 | 
118 |   A "Standard Interface" means an interface that either is an official
119 | standard defined by a recognized standards body, or, in the case of
120 | interfaces specified for a particular programming language, one that
121 | is widely used among developers working in that language.
122 | 
123 |   The "System Libraries" of an executable work include anything, other
124 | than the work as a whole, that (a) is included in the normal form of
125 | packaging a Major Component, but which is not part of that Major
126 | Component, and (b) serves only to enable use of the work with that
127 | Major Component, or to implement a Standard Interface for which an
128 | implementation is available to the public in source code form.  A
129 | "Major Component", in this context, means a major essential component
130 | (kernel, window system, and so on) of the specific operating system
131 | (if any) on which the executable work runs, or a compiler used to
132 | produce the work, or an object code interpreter used to run it.
133 | 
134 |   The "Corresponding Source" for a work in object code form means all
135 | the source code needed to generate, install, and (for an executable
136 | work) run the object code and to modify the work, including scripts to
137 | control those activities.  However, it does not include the work's
138 | System Libraries, or general-purpose tools or generally available free
139 | programs which are used unmodified in performing those activities but
140 | which are not part of the work.  For example, Corresponding Source
141 | includes interface definition files associated with source files for
142 | the work, and the source code for shared libraries and dynamically
143 | linked subprograms that the work is specifically designed to require,
144 | such as by intimate data communication or control flow between those
145 | subprograms and other parts of the work.
146 | 
147 |   The Corresponding Source need not include anything that users
148 | can regenerate automatically from other parts of the Corresponding
149 | Source.
150 | 
151 |   The Corresponding Source for a work in source code form is that
152 | same work.
153 | 
154 |   2. Basic Permissions.
155 | 
156 |   All rights granted under this License are granted for the term of
157 | copyright on the Program, and are irrevocable provided the stated
158 | conditions are met.  This License explicitly affirms your unlimited
159 | permission to run the unmodified Program.  The output from running a
160 | covered work is covered by this License only if the output, given its
161 | content, constitutes a covered work.  This License acknowledges your
162 | rights of fair use or other equivalent, as provided by copyright law.
163 | 
164 |   You may make, run and propagate covered works that you do not
165 | convey, without conditions so long as your license otherwise remains
166 | in force.  You may convey covered works to others for the sole purpose
167 | of having them make modifications exclusively for you, or provide you
168 | with facilities for running those works, provided that you comply with
169 | the terms of this License in conveying all material for which you do
170 | not control copyright.  Those thus making or running the covered works
171 | for you must do so exclusively on your behalf, under your direction
172 | and control, on terms that prohibit them from making any copies of
173 | your copyrighted material outside their relationship with you.
174 | 
175 |   Conveying under any other circumstances is permitted solely under
176 | the conditions stated below.  Sublicensing is not allowed; section 10
177 | makes it unnecessary.
178 | 
179 |   3. Protecting Users' Legal Rights From Anti-Circumvention Law.
180 | 
181 |   No covered work shall be deemed part of an effective technological
182 | measure under any applicable law fulfilling obligations under article
183 | 11 of the WIPO copyright treaty adopted on 20 December 1996, or
184 | similar laws prohibiting or restricting circumvention of such
185 | measures.
186 | 
187 |   When you convey a covered work, you waive any legal power to forbid
188 | circumvention of technological measures to the extent such circumvention
189 | is effected by exercising rights under this License with respect to
190 | the covered work, and you disclaim any intention to limit operation or
191 | modification of the work as a means of enforcing, against the work's
192 | users, your or third parties' legal rights to forbid circumvention of
193 | technological measures.
194 | 
195 |   4. Conveying Verbatim Copies.
196 | 
197 |   You may convey verbatim copies of the Program's source code as you
198 | receive it, in any medium, provided that you conspicuously and
199 | appropriately publish on each copy an appropriate copyright notice;
200 | keep intact all notices stating that this License and any
201 | non-permissive terms added in accord with section 7 apply to the code;
202 | keep intact all notices of the absence of any warranty; and give all
203 | recipients a copy of this License along with the Program.
204 | 
205 |   You may charge any price or no price for each copy that you convey,
206 | and you may offer support or warranty protection for a fee.
207 | 
208 |   5. Conveying Modified Source Versions.
209 | 
210 |   You may convey a work based on the Program, or the modifications to
211 | produce it from the Program, in the form of source code under the
212 | terms of section 4, provided that you also meet all of these conditions:
213 | 
214 |     a) The work must carry prominent notices stating that you modified
215 |     it, and giving a relevant date.
216 | 
217 |     b) The work must carry prominent notices stating that it is
218 |     released under this License and any conditions added under section
219 |     7.  This requirement modifies the requirement in section 4 to
220 |     "keep intact all notices".
221 | 
222 |     c) You must license the entire work, as a whole, under this
223 |     License to anyone who comes into possession of a copy.  This
224 |     License will therefore apply, along with any applicable section 7
225 |     additional terms, to the whole of the work, and all its parts,
226 |     regardless of how they are packaged.  This License gives no
227 |     permission to license the work in any other way, but it does not
228 |     invalidate such permission if you have separately received it.
229 | 
230 |     d) If the work has interactive user interfaces, each must display
231 |     Appropriate Legal Notices; however, if the Program has interactive
232 |     interfaces that do not display Appropriate Legal Notices, your
233 |     work need not make them do so.
234 | 
235 |   A compilation of a covered work with other separate and independent
236 | works, which are not by their nature extensions of the covered work,
237 | and which are not combined with it such as to form a larger program,
238 | in or on a volume of a storage or distribution medium, is called an
239 | "aggregate" if the compilation and its resulting copyright are not
240 | used to limit the access or legal rights of the compilation's users
241 | beyond what the individual works permit.  Inclusion of a covered work
242 | in an aggregate does not cause this License to apply to the other
243 | parts of the aggregate.
244 | 
245 |   6. Conveying Non-Source Forms.
246 | 
247 |   You may convey a covered work in object code form under the terms
248 | of sections 4 and 5, provided that you also convey the
249 | machine-readable Corresponding Source under the terms of this License,
250 | in one of these ways:
251 | 
252 |     a) Convey the object code in, or embodied in, a physical product
253 |     (including a physical distribution medium), accompanied by the
254 |     Corresponding Source fixed on a durable physical medium
255 |     customarily used for software interchange.
256 | 
257 |     b) Convey the object code in, or embodied in, a physical product
258 |     (including a physical distribution medium), accompanied by a
259 |     written offer, valid for at least three years and valid for as
260 |     long as you offer spare parts or customer support for that product
261 |     model, to give anyone who possesses the object code either (1) a
262 |     copy of the Corresponding Source for all the software in the
263 |     product that is covered by this License, on a durable physical
264 |     medium customarily used for software interchange, for a price no
265 |     more than your reasonable cost of physically performing this
266 |     conveying of source, or (2) access to copy the
267 |     Corresponding Source from a network server at no charge.
268 | 
269 |     c) Convey individual copies of the object code with a copy of the
270 |     written offer to provide the Corresponding Source.  This
271 |     alternative is allowed only occasionally and noncommercially, and
272 |     only if you received the object code with such an offer, in accord
273 |     with subsection 6b.
274 | 
275 |     d) Convey the object code by offering access from a designated
276 |     place (gratis or for a charge), and offer equivalent access to the
277 |     Corresponding Source in the same way through the same place at no
278 |     further charge.  You need not require recipients to copy the
279 |     Corresponding Source along with the object code.  If the place to
280 |     copy the object code is a network server, the Corresponding Source
281 |     may be on a different server (operated by you or a third party)
282 |     that supports equivalent copying facilities, provided you maintain
283 |     clear directions next to the object code saying where to find the
284 |     Corresponding Source.  Regardless of what server hosts the
285 |     Corresponding Source, you remain obligated to ensure that it is
286 |     available for as long as needed to satisfy these requirements.
287 | 
288 |     e) Convey the object code using peer-to-peer transmission, provided
289 |     you inform other peers where the object code and Corresponding
290 |     Source of the work are being offered to the general public at no
291 |     charge under subsection 6d.
292 | 
293 |   A separable portion of the object code, whose source code is excluded
294 | from the Corresponding Source as a System Library, need not be
295 | included in conveying the object code work.
296 | 
297 |   A "User Product" is either (1) a "consumer product", which means any
298 | tangible personal property which is normally used for personal, family,
299 | or household purposes, or (2) anything designed or sold for incorporation
300 | into a dwelling.  In determining whether a product is a consumer product,
301 | doubtful cases shall be resolved in favor of coverage.  For a particular
302 | product received by a particular user, "normally used" refers to a
303 | typical or common use of that class of product, regardless of the status
304 | of the particular user or of the way in which the particular user
305 | actually uses, or expects or is expected to use, the product.  A product
306 | is a consumer product regardless of whether the product has substantial
307 | commercial, industrial or non-consumer uses, unless such uses represent
308 | the only significant mode of use of the product.
309 | 
310 |   "Installation Information" for a User Product means any methods,
311 | procedures, authorization keys, or other information required to install
312 | and execute modified versions of a covered work in that User Product from
313 | a modified version of its Corresponding Source.  The information must
314 | suffice to ensure that the continued functioning of the modified object
315 | code is in no case prevented or interfered with solely because
316 | modification has been made.
317 | 
318 |   If you convey an object code work under this section in, or with, or
319 | specifically for use in, a User Product, and the conveying occurs as
320 | part of a transaction in which the right of possession and use of the
321 | User Product is transferred to the recipient in perpetuity or for a
322 | fixed term (regardless of how the transaction is characterized), the
323 | Corresponding Source conveyed under this section must be accompanied
324 | by the Installation Information.  But this requirement does not apply
325 | if neither you nor any third party retains the ability to install
326 | modified object code on the User Product (for example, the work has
327 | been installed in ROM).
328 | 
329 |   The requirement to provide Installation Information does not include a
330 | requirement to continue to provide support service, warranty, or updates
331 | for a work that has been modified or installed by the recipient, or for
332 | the User Product in which it has been modified or installed.  Access to a
333 | network may be denied when the modification itself materially and
334 | adversely affects the operation of the network or violates the rules and
335 | protocols for communication across the network.
336 | 
337 |   Corresponding Source conveyed, and Installation Information provided,
338 | in accord with this section must be in a format that is publicly
339 | documented (and with an implementation available to the public in
340 | source code form), and must require no special password or key for
341 | unpacking, reading or copying.
342 | 
343 |   7. Additional Terms.
344 | 
345 |   "Additional permissions" are terms that supplement the terms of this
346 | License by making exceptions from one or more of its conditions.
347 | Additional permissions that are applicable to the entire Program shall
348 | be treated as though they were included in this License, to the extent
349 | that they are valid under applicable law.  If additional permissions
350 | apply only to part of the Program, that part may be used separately
351 | under those permissions, but the entire Program remains governed by
352 | this License without regard to the additional permissions.
353 | 
354 |   When you convey a copy of a covered work, you may at your option
355 | remove any additional permissions from that copy, or from any part of
356 | it.  (Additional permissions may be written to require their own
357 | removal in certain cases when you modify the work.)  You may place
358 | additional permissions on material, added by you to a covered work,
359 | for which you have or can give appropriate copyright permission.
360 | 
361 |   Notwithstanding any other provision of this License, for material you
362 | add to a covered work, you may (if authorized by the copyright holders of
363 | that material) supplement the terms of this License with terms:
364 | 
365 |     a) Disclaiming warranty or limiting liability differently from the
366 |     terms of sections 15 and 16 of this License; or
367 | 
368 |     b) Requiring preservation of specified reasonable legal notices or
369 |     author attributions in that material or in the Appropriate Legal
370 |     Notices displayed by works containing it; or
371 | 
372 |     c) Prohibiting misrepresentation of the origin of that material, or
373 |     requiring that modified versions of such material be marked in
374 |     reasonable ways as different from the original version; or
375 | 
376 |     d) Limiting the use for publicity purposes of names of licensors or
377 |     authors of the material; or
378 | 
379 |     e) Declining to grant rights under trademark law for use of some
380 |     trade names, trademarks, or service marks; or
381 | 
382 |     f) Requiring indemnification of licensors and authors of that
383 |     material by anyone who conveys the material (or modified versions of
384 |     it) with contractual assumptions of liability to the recipient, for
385 |     any liability that these contractual assumptions directly impose on
386 |     those licensors and authors.
387 | 
388 |   All other non-permissive additional terms are considered "further
389 | restrictions" within the meaning of section 10.  If the Program as you
390 | received it, or any part of it, contains a notice stating that it is
391 | governed by this License along with a term that is a further
392 | restriction, you may remove that term.  If a license document contains
393 | a further restriction but permits relicensing or conveying under this
394 | License, you may add to a covered work material governed by the terms
395 | of that license document, provided that the further restriction does
396 | not survive such relicensing or conveying.
397 | 
398 |   If you add terms to a covered work in accord with this section, you
399 | must place, in the relevant source files, a statement of the
400 | additional terms that apply to those files, or a notice indicating
401 | where to find the applicable terms.
402 | 
403 |   Additional terms, permissive or non-permissive, may be stated in the
404 | form of a separately written license, or stated as exceptions;
405 | the above requirements apply either way.
406 | 
407 |   8. Termination.
408 | 
409 |   You may not propagate or modify a covered work except as expressly
410 | provided under this License.  Any attempt otherwise to propagate or
411 | modify it is void, and will automatically terminate your rights under
412 | this License (including any patent licenses granted under the third
413 | paragraph of section 11).
414 | 
415 |   However, if you cease all violation of this License, then your
416 | license from a particular copyright holder is reinstated (a)
417 | provisionally, unless and until the copyright holder explicitly and
418 | finally terminates your license, and (b) permanently, if the copyright
419 | holder fails to notify you of the violation by some reasonable means
420 | prior to 60 days after the cessation.
421 | 
422 |   Moreover, your license from a particular copyright holder is
423 | reinstated permanently if the copyright holder notifies you of the
424 | violation by some reasonable means, this is the first time you have
425 | received notice of violation of this License (for any work) from that
426 | copyright holder, and you cure the violation prior to 30 days after
427 | your receipt of the notice.
428 | 
429 |   Termination of your rights under this section does not terminate the
430 | licenses of parties who have received copies or rights from you under
431 | this License.  If your rights have been terminated and not permanently
432 | reinstated, you do not qualify to receive new licenses for the same
433 | material under section 10.
434 | 
435 |   9. Acceptance Not Required for Having Copies.
436 | 
437 |   You are not required to accept this License in order to receive or
438 | run a copy of the Program.  Ancillary propagation of a covered work
439 | occurring solely as a consequence of using peer-to-peer transmission
440 | to receive a copy likewise does not require acceptance.  However,
441 | nothing other than this License grants you permission to propagate or
442 | modify any covered work.  These actions infringe copyright if you do
443 | not accept this License.  Therefore, by modifying or propagating a
444 | covered work, you indicate your acceptance of this License to do so.
445 | 
446 |   10. Automatic Licensing of Downstream Recipients.
447 | 
448 |   Each time you convey a covered work, the recipient automatically
449 | receives a license from the original licensors, to run, modify and
450 | propagate that work, subject to this License.  You are not responsible
451 | for enforcing compliance by third parties with this License.
452 | 
453 |   An "entity transaction" is a transaction transferring control of an
454 | organization, or substantially all assets of one, or subdividing an
455 | organization, or merging organizations.  If propagation of a covered
456 | work results from an entity transaction, each party to that
457 | transaction who receives a copy of the work also receives whatever
458 | licenses to the work the party's predecessor in interest had or could
459 | give under the previous paragraph, plus a right to possession of the
460 | Corresponding Source of the work from the predecessor in interest, if
461 | the predecessor has it or can get it with reasonable efforts.
462 | 
463 |   You may not impose any further restrictions on the exercise of the
464 | rights granted or affirmed under this License.  For example, you may
465 | not impose a license fee, royalty, or other charge for exercise of
466 | rights granted under this License, and you may not initiate litigation
467 | (including a cross-claim or counterclaim in a lawsuit) alleging that
468 | any patent claim is infringed by making, using, selling, offering for
469 | sale, or importing the Program or any portion of it.
470 | 
471 |   11. Patents.
472 | 
473 |   A "contributor" is a copyright holder who authorizes use under this
474 | License of the Program or a work on which the Program is based.  The
475 | work thus licensed is called the contributor's "contributor version".
476 | 
477 |   A contributor's "essential patent claims" are all patent claims
478 | owned or controlled by the contributor, whether already acquired or
479 | hereafter acquired, that would be infringed by some manner, permitted
480 | by this License, of making, using, or selling its contributor version,
481 | but do not include claims that would be infringed only as a
482 | consequence of further modification of the contributor version.  For
483 | purposes of this definition, "control" includes the right to grant
484 | patent sublicenses in a manner consistent with the requirements of
485 | this License.
486 | 
487 |   Each contributor grants you a non-exclusive, worldwide, royalty-free
488 | patent license under the contributor's essential patent claims, to
489 | make, use, sell, offer for sale, import and otherwise run, modify and
490 | propagate the contents of its contributor version.
491 | 
492 |   In the following three paragraphs, a "patent license" is any express
493 | agreement or commitment, however denominated, not to enforce a patent
494 | (such as an express permission to practice a patent or covenant not to
495 | sue for patent infringement).  To "grant" such a patent license to a
496 | party means to make such an agreement or commitment not to enforce a
497 | patent against the party.
498 | 
499 |   If you convey a covered work, knowingly relying on a patent license,
500 | and the Corresponding Source of the work is not available for anyone
501 | to copy, free of charge and under the terms of this License, through a
502 | publicly available network server or other readily accessible means,
503 | then you must either (1) cause the Corresponding Source to be so
504 | available, or (2) arrange to deprive yourself of the benefit of the
505 | patent license for this particular work, or (3) arrange, in a manner
506 | consistent with the requirements of this License, to extend the patent
507 | license to downstream recipients.  "Knowingly relying" means you have
508 | actual knowledge that, but for the patent license, your conveying the
509 | covered work in a country, or your recipient's use of the covered work
510 | in a country, would infringe one or more identifiable patents in that
511 | country that you have reason to believe are valid.
512 | 
513 |   If, pursuant to or in connection with a single transaction or
514 | arrangement, you convey, or propagate by procuring conveyance of, a
515 | covered work, and grant a patent license to some of the parties
516 | receiving the covered work authorizing them to use, propagate, modify
517 | or convey a specific copy of the covered work, then the patent license
518 | you grant is automatically extended to all recipients of the covered
519 | work and works based on it.
520 | 
521 |   A patent license is "discriminatory" if it does not include within
522 | the scope of its coverage, prohibits the exercise of, or is
523 | conditioned on the non-exercise of one or more of the rights that are
524 | specifically granted under this License.  You may not convey a covered
525 | work if you are a party to an arrangement with a third party that is
526 | in the business of distributing software, under which you make payment
527 | to the third party based on the extent of your activity of conveying
528 | the work, and under which the third party grants, to any of the
529 | parties who would receive the covered work from you, a discriminatory
530 | patent license (a) in connection with copies of the covered work
531 | conveyed by you (or copies made from those copies), or (b) primarily
532 | for and in connection with specific products or compilations that
533 | contain the covered work, unless you entered into that arrangement,
534 | or that patent license was granted, prior to 28 March 2007.
535 | 
536 |   Nothing in this License shall be construed as excluding or limiting
537 | any implied license or other defenses to infringement that may
538 | otherwise be available to you under applicable patent law.
539 | 
540 |   12. No Surrender of Others' Freedom.
541 | 
542 |   If conditions are imposed on you (whether by court order, agreement or
543 | otherwise) that contradict the conditions of this License, they do not
544 | excuse you from the conditions of this License.  If you cannot convey a
545 | covered work so as to satisfy simultaneously your obligations under this
546 | License and any other pertinent obligations, then as a consequence you may
547 | not convey it at all.  For example, if you agree to terms that obligate you
548 | to collect a royalty for further conveying from those to whom you convey
549 | the Program, the only way you could satisfy both those terms and this
550 | License would be to refrain entirely from conveying the Program.
551 | 
552 |   13. Use with the GNU Affero General Public License.
553 | 
554 |   Notwithstanding any other provision of this License, you have
555 | permission to link or combine any covered work with a work licensed
556 | under version 3 of the GNU Affero General Public License into a single
557 | combined work, and to convey the resulting work.  The terms of this
558 | License will continue to apply to the part which is the covered work,
559 | but the special requirements of the GNU Affero General Public License,
560 | section 13, concerning interaction through a network will apply to the
561 | combination as such.
562 | 
563 |   14. Revised Versions of this License.
564 | 
565 |   The Free Software Foundation may publish revised and/or new versions of
566 | the GNU General Public License from time to time.  Such new versions will
567 | be similar in spirit to the present version, but may differ in detail to
568 | address new problems or concerns.
569 | 
570 |   Each version is given a distinguishing version number.  If the
571 | Program specifies that a certain numbered version of the GNU General
572 | Public License "or any later version" applies to it, you have the
573 | option of following the terms and conditions either of that numbered
574 | version or of any later version published by the Free Software
575 | Foundation.  If the Program does not specify a version number of the
576 | GNU General Public License, you may choose any version ever published
577 | by the Free Software Foundation.
578 | 
579 |   If the Program specifies that a proxy can decide which future
580 | versions of the GNU General Public License can be used, that proxy's
581 | public statement of acceptance of a version permanently authorizes you
582 | to choose that version for the Program.
583 | 
584 |   Later license versions may give you additional or different
585 | permissions.  However, no additional obligations are imposed on any
586 | author or copyright holder as a result of your choosing to follow a
587 | later version.
588 | 
589 |   15. Disclaimer of Warranty.
590 | 
591 |   THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY
592 | APPLICABLE LAW.  EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT
593 | HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY
594 | OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO,
595 | THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
596 | PURPOSE.  THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM
597 | IS WITH YOU.  SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF
598 | ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
599 | 
600 |   16. Limitation of Liability.
601 | 
602 |   IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
603 | WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS
604 | THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY
605 | GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE
606 | USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF
607 | DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD
608 | PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS),
609 | EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF
610 | SUCH DAMAGES.
611 | 
612 |   17. Interpretation of Sections 15 and 16.
613 | 
614 |   If the disclaimer of warranty and limitation of liability provided
615 | above cannot be given local legal effect according to their terms,
616 | reviewing courts shall apply local law that most closely approximates
617 | an absolute waiver of all civil liability in connection with the
618 | Program, unless a warranty or assumption of liability accompanies a
619 | copy of the Program in return for a fee.
620 | 
621 |                      END OF TERMS AND CONDITIONS
622 | 
623 |             How to Apply These Terms to Your New Programs
624 | 
625 |   If you develop a new program, and you want it to be of the greatest
626 | possible use to the public, the best way to achieve this is to make it
627 | free software which everyone can redistribute and change under these terms.
628 | 
629 |   To do so, attach the following notices to the program.  It is safest
630 | to attach them to the start of each source file to most effectively
631 | state the exclusion of warranty; and each file should have at least
632 | the "copyright" line and a pointer to where the full notice is found.
633 | 
634 |     <one line to give the program's name and a brief idea of what it does.>
635 |     Copyright (C) <year>  <name of author>
636 | 
637 |     This program is free software: you can redistribute it and/or modify
638 |     it under the terms of the GNU General Public License as published by
639 |     the Free Software Foundation, either version 3 of the License, or
640 |     (at your option) any later version.
641 | 
642 |     This program is distributed in the hope that it will be useful,
643 |     but WITHOUT ANY WARRANTY; without even the implied warranty of
644 |     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
645 |     GNU General Public License for more details.
646 | 
647 |     You should have received a copy of the GNU General Public License
648 |     along with this program.  If not, see <https://www.gnu.org/licenses/>.
649 | 
650 | Also add information on how to contact you by electronic and paper mail.
651 | 
652 |   If the program does terminal interaction, make it output a short
653 | notice like this when it starts in an interactive mode:
654 | 
655 |     <program>  Copyright (C) <year>  <name of author>
656 |     This program comes with ABSOLUTELY NO WARRANTY; for details type `show w'.
657 |     This is free software, and you are welcome to redistribute it
658 |     under certain conditions; type `show c' for details.
659 | 
660 | The hypothetical commands `show w' and `show c' should show the appropriate
661 | parts of the General Public License.  Of course, your program's commands
662 | might be different; for a GUI interface, you would use an "about box".
663 | 
664 |   You should also get your employer (if you work as a programmer) or school,
665 | if any, to sign a "copyright disclaimer" for the program, if necessary.
666 | For more information on this, and how to apply and follow the GNU GPL, see
667 | <https://www.gnu.org/licenses/>.
668 | 
669 |   The GNU General Public License does not permit incorporating your program
670 | into proprietary programs.  If your program is a subroutine library, you
671 | may consider it more useful to permit linking proprietary applications with
672 | the library.  If this is what you want to do, use the GNU Lesser General
673 | Public License instead of this License.  But first, please read
674 | <https://www.gnu.org/licenses/why-not-lgpl.html>.
675 | 


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