├── .gitignore ├── CHANGELOG.rst ├── LICENSE ├── MANIFEST.in ├── Makefile ├── README.rst ├── examples ├── change_min_block_size.py ├── named_markers.py ├── parsing_files.py ├── pre_processed_template.py ├── save_open_dump_load.py ├── simple_example.py └── strings_with_markers_as_template.py ├── requirements └── development.txt ├── run-tests.sh ├── setup.py ├── templater.c ├── templater.py └── tests ├── test_Templater.py ├── test_create_template.py └── test_parser.py /.gitignore: -------------------------------------------------------------------------------- 1 | *~ 2 | *.sw[a-z] 3 | *.pyc 4 | build/ 5 | reg_settings* 6 | _templater.so 7 | .coverage 8 | -------------------------------------------------------------------------------- /CHANGELOG.rst: -------------------------------------------------------------------------------- 1 | Changelog 2 | ========= 3 | 4 | Version 0.4.0 5 | ------------- 6 | 7 | - Released at: 2012-04-24 15:07:58. 8 | - `New feature `_: named markers 9 | (new method ``add_headers``). 10 | - `Bug fixed `_: last blank 11 | wasn't being filled. 12 | - `Bug fixed `_: ignoring 13 | ``\r\n``/``\n`` in the end of files in ``save`` and ``open`` methods. 14 | - `New Feature `_: added method 15 | ``parse_file``. 16 | - `Enhancement `_: renamed 17 | ``tolerance`` to ``min_block_size``. 18 | - Enhancement: refactored tests. 19 | - Enhancement: refactored ``README.rst``. 20 | - Enhancement: created ``CHANGELOG.rst``. 21 | 22 | 23 | Version 0.3.0 24 | ------------- 25 | 26 | - Released at: 2012-04-20 20:09:52. 27 | - Enhancement: method ``save`` renamed to ``dump``. 28 | - New feature: new methods ``save`` and ``open`` - saves and open the template 29 | to/from a document (file) - do not pickle the entire object as ``dump`` and 30 | ``load``. 31 | - Enhancement: using nose coverage plugin. 32 | 33 | 34 | Version 0.2.1 35 | ------------- 36 | 37 | - Released at: 2012-04-30 18:34:35. 38 | - Bug fixed: replaced ``README.markdown`` with ``README.rst`` in 39 | ``MANIFEST.in``. 40 | 41 | 42 | Version 0.2.0 43 | ------------- 44 | 45 | - Released at: 2012-04-20 18:30:23. 46 | - `New feature `_: ``tolerance`` 47 | (min block size). 48 | - Bug fixed: ``save`` and ``load`` now pickle the entire object (instead of 49 | only template definition). 50 | 51 | 52 | Version 0.1.1 53 | ------------- 54 | 55 | - Released at: 2012-04-20 15:08:05. 56 | - Enhancement: ``README.markdown`` is now ``README.rst`` (reStructuredText). 57 | 58 | 59 | Version 0.1.0 60 | ------------- 61 | 62 | - Released at: 2012-04-20 14:57:44. 63 | - First working version (``learn`` and ``parse`` methods created). 64 | - New feature: ``save`` and ``load`` methods created. 65 | - New feature: ``join`` method created. 66 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | GNU GENERAL PUBLIC LICENSE 2 | Version 2, June 1991 3 | 4 | Copyright (C) 1989, 1991 Free Software Foundation, Inc., 5 | 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA 6 | Everyone is permitted to copy and distribute verbatim copies 7 | of this license document, but changing it is not allowed. 8 | 9 | Preamble 10 | 11 | The licenses for most software are designed to take away your 12 | freedom to share and change it. By contrast, the GNU General Public 13 | License is intended to guarantee your freedom to share and change free 14 | software--to make sure the software is free for all its users. This 15 | General Public License applies to most of the Free Software 16 | Foundation's software and to any other program whose authors commit to 17 | using it. (Some other Free Software Foundation software is covered by 18 | the GNU Lesser General Public License instead.) You can apply it to 19 | your programs, too. 20 | 21 | When we speak of free software, we are referring to freedom, not 22 | price. Our General Public Licenses are designed to make sure that you 23 | have the freedom to distribute copies of free software (and charge for 24 | this service if you wish), that you receive source code or can get it 25 | if you want it, that you can change the software or use pieces of it 26 | in new free programs; and that you know you can do these things. 27 | 28 | To protect your rights, we need to make restrictions that forbid 29 | anyone to deny you these rights or to ask you to surrender the rights. 30 | These restrictions translate to certain responsibilities for you if you 31 | distribute copies of the software, or if you modify it. 32 | 33 | For example, if you distribute copies of such a program, whether 34 | gratis or for a fee, you must give the recipients all the rights that 35 | you have. You must make sure that they, too, receive or can get the 36 | source code. And you must show them these terms so they know their 37 | rights. 38 | 39 | We protect your rights with two steps: (1) copyright the software, and 40 | (2) offer you this license which gives you legal permission to copy, 41 | distribute and/or modify the software. 42 | 43 | Also, for each author's protection and ours, we want to make certain 44 | that everyone understands that there is no warranty for this free 45 | software. If the software is modified by someone else and passed on, we 46 | want its recipients to know that what they have is not the original, so 47 | that any problems introduced by others will not reflect on the original 48 | authors' reputations. 49 | 50 | Finally, any free program is threatened constantly by software 51 | patents. We wish to avoid the danger that redistributors of a free 52 | program will individually obtain patent licenses, in effect making the 53 | program proprietary. To prevent this, we have made it clear that any 54 | patent must be licensed for everyone's free use or not licensed at all. 55 | 56 | The precise terms and conditions for copying, distribution and 57 | modification follow. 58 | 59 | GNU GENERAL PUBLIC LICENSE 60 | TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION 61 | 62 | 0. This License applies to any program or other work which contains 63 | a notice placed by the copyright holder saying it may be distributed 64 | under the terms of this General Public License. The "Program", below, 65 | refers to any such program or work, and a "work based on the Program" 66 | means either the Program or any derivative work under copyright law: 67 | that is to say, a work containing the Program or a portion of it, 68 | either verbatim or with modifications and/or translated into another 69 | language. (Hereinafter, translation is included without limitation in 70 | the term "modification".) Each licensee is addressed as "you". 71 | 72 | Activities other than copying, distribution and modification are not 73 | covered by this License; they are outside its scope. The act of 74 | running the Program is not restricted, and the output from the Program 75 | is covered only if its contents constitute a work based on the 76 | Program (independent of having been made by running the Program). 77 | Whether that is true depends on what the Program does. 78 | 79 | 1. You may copy and distribute verbatim copies of the Program's 80 | source code as you receive it, in any medium, provided that you 81 | conspicuously and appropriately publish on each copy an appropriate 82 | copyright notice and disclaimer of warranty; keep intact all the 83 | notices that refer to this License and to the absence of any warranty; 84 | and give any other recipients of the Program a copy of this License 85 | along with the Program. 86 | 87 | You may charge a fee for the physical act of transferring a copy, and 88 | you may at your option offer warranty protection in exchange for a fee. 89 | 90 | 2. You may modify your copy or copies of the Program or any portion 91 | of it, thus forming a work based on the Program, and copy and 92 | distribute such modifications or work under the terms of Section 1 93 | above, provided that you also meet all of these conditions: 94 | 95 | a) You must cause the modified files to carry prominent notices 96 | stating that you changed the files and the date of any change. 97 | 98 | b) You must cause any work that you distribute or publish, that in 99 | whole or in part contains or is derived from the Program or any 100 | part thereof, to be licensed as a whole at no charge to all third 101 | parties under the terms of this License. 102 | 103 | c) If the modified program normally reads commands interactively 104 | when run, you must cause it, when started running for such 105 | interactive use in the most ordinary way, to print or display an 106 | announcement including an appropriate copyright notice and a 107 | notice that there is no warranty (or else, saying that you provide 108 | a warranty) and that users may redistribute the program under 109 | these conditions, and telling the user how to view a copy of this 110 | License. (Exception: if the Program itself is interactive but 111 | does not normally print such an announcement, your work based on 112 | the Program is not required to print an announcement.) 113 | 114 | These requirements apply to the modified work as a whole. If 115 | identifiable sections of that work are not derived from the Program, 116 | and can be reasonably considered independent and separate works in 117 | themselves, then this License, and its terms, do not apply to those 118 | sections when you distribute them as separate works. But when you 119 | distribute the same sections as part of a whole which is a work based 120 | on the Program, the distribution of the whole must be on the terms of 121 | this License, whose permissions for other licensees extend to the 122 | entire whole, and thus to each and every part regardless of who wrote it. 123 | 124 | Thus, it is not the intent of this section to claim rights or contest 125 | your rights to work written entirely by you; rather, the intent is to 126 | exercise the right to control the distribution of derivative or 127 | collective works based on the Program. 128 | 129 | In addition, mere aggregation of another work not based on the Program 130 | with the Program (or with a work based on the Program) on a volume of 131 | a storage or distribution medium does not bring the other work under 132 | the scope of this License. 133 | 134 | 3. You may copy and distribute the Program (or a work based on it, 135 | under Section 2) in object code or executable form under the terms of 136 | Sections 1 and 2 above provided that you also do one of the following: 137 | 138 | a) Accompany it with the complete corresponding machine-readable 139 | source code, which must be distributed under the terms of Sections 140 | 1 and 2 above on a medium customarily used for software interchange; or, 141 | 142 | b) Accompany it with a written offer, valid for at least three 143 | years, to give any third party, for a charge no more than your 144 | cost of physically performing source distribution, a complete 145 | machine-readable copy of the corresponding source code, to be 146 | distributed under the terms of Sections 1 and 2 above on a medium 147 | customarily used for software interchange; or, 148 | 149 | c) Accompany it with the information you received as to the offer 150 | to distribute corresponding source code. (This alternative is 151 | allowed only for noncommercial distribution and only if you 152 | received the program in object code or executable form with such 153 | an offer, in accord with Subsection b above.) 154 | 155 | The source code for a work means the preferred form of the work for 156 | making modifications to it. For an executable work, complete source 157 | code means all the source code for all modules it contains, plus any 158 | associated interface definition files, plus the scripts used to 159 | control compilation and installation of the executable. However, as a 160 | special exception, the source code distributed need not include 161 | anything that is normally distributed (in either source or binary 162 | form) with the major components (compiler, kernel, and so on) of the 163 | operating system on which the executable runs, unless that component 164 | itself accompanies the executable. 165 | 166 | If distribution of executable or object code is made by offering 167 | access to copy from a designated place, then offering equivalent 168 | access to copy the source code from the same place counts as 169 | distribution of the source code, even though third parties are not 170 | compelled to copy the source along with the object code. 171 | 172 | 4. You may not copy, modify, sublicense, or distribute the Program 173 | except as expressly provided under this License. Any attempt 174 | otherwise to copy, modify, sublicense or distribute the Program is 175 | void, and will automatically terminate your rights under this License. 176 | However, parties who have received copies, or rights, from you under 177 | this License will not have their licenses terminated so long as such 178 | parties remain in full compliance. 179 | 180 | 5. You are not required to accept this License, since you have not 181 | signed it. However, nothing else grants you permission to modify or 182 | distribute the Program or its derivative works. These actions are 183 | prohibited by law if you do not accept this License. Therefore, by 184 | modifying or distributing the Program (or any work based on the 185 | Program), you indicate your acceptance of this License to do so, and 186 | all its terms and conditions for copying, distributing or modifying 187 | the Program or works based on it. 188 | 189 | 6. Each time you redistribute the Program (or any work based on the 190 | Program), the recipient automatically receives a license from the 191 | original licensor to copy, distribute or modify the Program subject to 192 | these terms and conditions. You may not impose any further 193 | restrictions on the recipients' exercise of the rights granted herein. 194 | You are not responsible for enforcing compliance by third parties to 195 | this License. 196 | 197 | 7. If, as a consequence of a court judgment or allegation of patent 198 | infringement or for any other reason (not limited to patent issues), 199 | conditions are imposed on you (whether by court order, agreement or 200 | otherwise) that contradict the conditions of this License, they do not 201 | excuse you from the conditions of this License. If you cannot 202 | distribute so as to satisfy simultaneously your obligations under this 203 | License and any other pertinent obligations, then as a consequence you 204 | may not distribute the Program at all. For example, if a patent 205 | license would not permit royalty-free redistribution of the Program by 206 | all those who receive copies directly or indirectly through you, then 207 | the only way you could satisfy both it and this License would be to 208 | refrain entirely from distribution of the Program. 209 | 210 | If any portion of this section is held invalid or unenforceable under 211 | any particular circumstance, the balance of the section is intended to 212 | apply and the section as a whole is intended to apply in other 213 | circumstances. 214 | 215 | It is not the purpose of this section to induce you to infringe any 216 | patents or other property right claims or to contest validity of any 217 | such claims; this section has the sole purpose of protecting the 218 | integrity of the free software distribution system, which is 219 | implemented by public license practices. Many people have made 220 | generous contributions to the wide range of software distributed 221 | through that system in reliance on consistent application of that 222 | system; it is up to the author/donor to decide if he or she is willing 223 | to distribute software through any other system and a licensee cannot 224 | impose that choice. 225 | 226 | This section is intended to make thoroughly clear what is believed to 227 | be a consequence of the rest of this License. 228 | 229 | 8. If the distribution and/or use of the Program is restricted in 230 | certain countries either by patents or by copyrighted interfaces, the 231 | original copyright holder who places the Program under this License 232 | may add an explicit geographical distribution limitation excluding 233 | those countries, so that distribution is permitted only in or among 234 | countries not thus excluded. In such case, this License incorporates 235 | the limitation as if written in the body of this License. 236 | 237 | 9. The Free Software Foundation may publish revised and/or new versions 238 | of the General Public License from time to time. Such new versions will 239 | be similar in spirit to the present version, but may differ in detail to 240 | address new problems or concerns. 241 | 242 | Each version is given a distinguishing version number. If the Program 243 | specifies a version number of this License which applies to it and "any 244 | later version", you have the option of following the terms and conditions 245 | either of that version or of any later version published by the Free 246 | Software Foundation. If the Program does not specify a version number of 247 | this License, you may choose any version ever published by the Free Software 248 | Foundation. 249 | 250 | 10. If you wish to incorporate parts of the Program into other free 251 | programs whose distribution conditions are different, write to the author 252 | to ask for permission. For software which is copyrighted by the Free 253 | Software Foundation, write to the Free Software Foundation; we sometimes 254 | make exceptions for this. Our decision will be guided by the two goals 255 | of preserving the free status of all derivatives of our free software and 256 | of promoting the sharing and reuse of software generally. 257 | 258 | NO WARRANTY 259 | 260 | 11. BECAUSE THE PROGRAM IS LICENSED FREE OF CHARGE, THERE IS NO WARRANTY 261 | FOR THE PROGRAM, TO THE EXTENT PERMITTED BY APPLICABLE LAW. EXCEPT WHEN 262 | OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES 263 | PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED 264 | OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF 265 | MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE. THE ENTIRE RISK AS 266 | TO THE QUALITY AND PERFORMANCE OF THE PROGRAM IS WITH YOU. SHOULD THE 267 | PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF ALL NECESSARY SERVICING, 268 | REPAIR OR CORRECTION. 269 | 270 | 12. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING 271 | WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY AND/OR 272 | REDISTRIBUTE THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, 273 | INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING 274 | OUT OF THE USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED 275 | TO LOSS OF DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY 276 | YOU OR THIRD PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER 277 | PROGRAMS), EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE 278 | POSSIBILITY OF SUCH DAMAGES. 279 | 280 | END OF TERMS AND CONDITIONS 281 | 282 | How to Apply These Terms to Your New Programs 283 | 284 | If you develop a new program, and you want it to be of the greatest 285 | possible use to the public, the best way to achieve this is to make it 286 | free software which everyone can redistribute and change under these terms. 287 | 288 | To do so, attach the following notices to the program. It is safest 289 | to attach them to the start of each source file to most effectively 290 | convey the exclusion of warranty; and each file should have at least 291 | the "copyright" line and a pointer to where the full notice is found. 292 | 293 | 294 | Copyright (C) 295 | 296 | This program is free software; you can redistribute it and/or modify 297 | it under the terms of the GNU General Public License as published by 298 | the Free Software Foundation; either version 2 of the License, or 299 | (at your option) any later version. 300 | 301 | This program is distributed in the hope that it will be useful, 302 | but WITHOUT ANY WARRANTY; without even the implied warranty of 303 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 304 | GNU General Public License for more details. 305 | 306 | You should have received a copy of the GNU General Public License along 307 | with this program; if not, write to the Free Software Foundation, Inc., 308 | 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. 309 | 310 | Also add information on how to contact you by electronic and paper mail. 311 | 312 | If the program is interactive, make it output a short notice like this 313 | when it starts in an interactive mode: 314 | 315 | Gnomovision version 69, Copyright (C) year name of author 316 | Gnomovision comes with ABSOLUTELY NO WARRANTY; for details type `show w'. 317 | This is free software, and you are welcome to redistribute it 318 | under certain conditions; type `show c' for details. 319 | 320 | The hypothetical commands `show w' and `show c' should show the appropriate 321 | parts of the General Public License. Of course, the commands you use may 322 | be called something other than `show w' and `show c'; they could even be 323 | mouse-clicks or menu items--whatever suits your program. 324 | 325 | You should also get your employer (if you work as a programmer) or your 326 | school, if any, to sign a "copyright disclaimer" for the program, if 327 | necessary. Here is a sample; alter the names: 328 | 329 | Yoyodyne, Inc., hereby disclaims all copyright interest in the program 330 | `Gnomovision' (which makes passes at compilers) written by James Hacker. 331 | 332 | , 1 April 1989 333 | Ty Coon, President of Vice 334 | 335 | This General Public License does not permit incorporating your program into 336 | proprietary programs. If your program is a subroutine library, you may 337 | consider it more useful to permit linking proprietary applications with the 338 | library. If this is what you want to do, use the GNU Lesser General 339 | Public License instead of this License. 340 | -------------------------------------------------------------------------------- /MANIFEST.in: -------------------------------------------------------------------------------- 1 | include README.rst 2 | include LICENSE 3 | include CHANGELOG.rst 4 | -------------------------------------------------------------------------------- /Makefile: -------------------------------------------------------------------------------- 1 | clean: 2 | rm -rf *.pyc **/*.pyc reg_settings* .coverage MANIFEST build/ dist/ \ 3 | _templater.so readme.html 4 | 5 | build: 6 | python setup.py build 7 | 8 | install: 9 | python setup.py install 10 | 11 | test: clean 12 | ./run-tests.sh 13 | make clean 14 | 15 | sdist: clean test 16 | python setup.py sdist 17 | 18 | upload: clean test 19 | python setup.py sdist upload 20 | make clean 21 | 22 | readme: 23 | rst2html README.rst > readme.html 24 | 25 | .PHONY: clean build install test sdist upload readme 26 | -------------------------------------------------------------------------------- /README.rst: -------------------------------------------------------------------------------- 1 | Templater 2 | ========= 3 | 4 | Introduction 5 | ------------ 6 | 7 | Given some strings (or files), this library extracts a common template between 8 | them (method ``learn``) -- some people call it "reverse templating". Having 9 | your template created, you can parse other strings/files using it - the 10 | ``parse`` method will return only what changes in this file (the "blanks"). It 11 | does something like the opposite of what template libraries (such as 12 | `Jinja `_) do. But for now, it only can identify 13 | fixed variables (it can't create ``for`` and ``if`` blocks, for example). 14 | 15 | If you have the template and the "blanks" you can also fill the blanks with 16 | the method ``join`` - it'll return a string with the template filled. There are 17 | some other features: 18 | 19 | - If you don't want/need to ``Templater`` (the main class) create the template 20 | for you, you can pass a pre-processed template (created manually or created 21 | before using ``learn`` and saved somewhere). 22 | - You can split the learning and parsing process, since the learning process 23 | generally is executed one time and takes a lot of time compared to parsing 24 | process. To turn this process handy, ``Templater`` has the methods ``dump``, 25 | ``save``, ``load`` and ``open``, so you can learn and save a template 26 | definition for later loading and parsing how many times you want (you can 27 | also load, learn more and save). 28 | 29 | `templater `_ is simple to use, easy to 30 | learn and does the hard work for you (for example: part of the learning 31 | algorithm is implemented in C for performance). Do you have 5 minutes? So learn 32 | with the `Examples`_. 33 | 34 | 35 | Installation 36 | ------------ 37 | 38 | `templater is available at PyPI `_, so 39 | installing it is as simple as executing:: 40 | 41 | pip install templater 42 | 43 | Or you can download the latest version and install it using ``setup.py``:: 44 | 45 | git clone https://turicas@github.com/turicas/templater.git 46 | cd templater 47 | python setup.py build install 48 | 49 | 50 | Terminology 51 | ----------- 52 | 53 | There are some definitions/concepts we should explicit here: 54 | 55 | - **Template**: the whole object (instance of ``Templater``). 56 | - **Document**: a string or file that have some kind of pattern. You'll use 57 | documents to make a template object learn and recognize these patterns, so 58 | later you can use the template object to parse a document and get only the 59 | information that is not "static". 60 | - **Blocks**: the fixed parts of a template. Can change (in number and size) 61 | when ``learn`` is run. 62 | - **Blanks**: also called holes or variables, blanks are the parts in a 63 | template that changes between documents with the same template. 64 | - **Template definition**: the information stored in a template that defines it 65 | (it is a Python list with a very simple grammar that describes how the 66 | template is composed). 67 | - **Markers**: when you want to save a template, something should be put 68 | between blocks to "mark" the blanks (so the template definition can be 69 | reconstructed later). 70 | - **Named marker**: a marker plus a header is called a named marker. They are 71 | handy and more legible since you can access the "blanks" by names instead of 72 | indexes. 73 | 74 | Doubts? Don't worry, see the `Examples`_ and you'll get it. 75 | 76 | 77 | Examples 78 | -------- 79 | 80 | All you need to know is below (and in the ``examples`` directory):: 81 | 82 | >>> from templater import Templater 83 | >>> documents_to_learn = [' spam and eggs ', ' ham and spam ', 84 | ' white and black '] # list of documents 85 | >>> template = Templater() 86 | >>> for document in documents_to_learn: 87 | ... template.learn(document) 88 | ... 89 | 90 | >>> print 'Template created:', template._template # template definition 91 | Template created: [None, ' ', None, ' and ', None, ' ', None] 92 | 93 | >>> document_to_parse = ' yellow and blue ' 94 | >>> print 'Parsing other document:', template.parse(document_to_parse) 95 | Parsing other document: ['', 'yellow', 'blue', ''] 96 | 97 | >>> print 'Filling the blanks:', template.join(['', 'red', 'orange', '']) 98 | Filling the blanks: red and orange 99 | 100 | You can pass pre-processed templates as a list (blanks are ``None``, blocks are 101 | strings):: 102 | 103 | >>> t2 = Templater(template=[None, 'Music: ', None, ', Band: ', None]) 104 | >>> print t2.join(['', 'Welcome to the Jungle', 'Guns and Roses']) 105 | Music: Welcome to the Jungle, Band: Guns and Roses 106 | 107 | ...or you can pass a string with markers, then ``Templater`` will create the 108 | list for you:: 109 | 110 | >>> t3 = Templater(template='language=#,cool=#', marker='#') 111 | >>> print t3.join(['', 'Python', 'YES', '']) 112 | language=Python,cool=YES 113 | 114 | Saving and opening templates is easy:: 115 | 116 | >>> template.save('my-first-template.html', marker='|||') 117 | >>> # and some time later... 118 | >>> loaded_template = Templater.open('my-first-template.html', marker='|||') 119 | >>> print loaded_template.parse(' Romeo and Juliet ') 120 | ['', 'Romeo', 'Juliet', ''] 121 | 122 | The difference between ``save`` and ``dump`` is that ``save`` stores the 123 | template string, filling the blanks with a marker and ``dump`` saves the whole 124 | ``Templater`` object with ``cPickle``. The pairs are: 125 | 126 | - ``save`` and ``open`` (raw template string filled with marker) 127 | - ``load`` and ``dump`` (whole object) 128 | 129 | **Note**: ``save`` always add a ``\n`` to the end of file; ``load`` 130 | deletes trailing ``\r\n`` or ``\n`` in the end of file (if any). 131 | 132 | **Note-2**: when passing a pre-processed template (using ``Templater`` 133 | initializer or ``Templater.open``) make sure it **starts and ends** with a 134 | marker. 135 | 136 | If you are getting a lot of blanks you can configure the learning process: just 137 | adjust ``min_block_size`` - it's the minimum number of characters permitted to 138 | create a new block in template:: 139 | 140 | >>> str_1 = 'my favorite color is blue' 141 | >>> str_2 = 'my favorite color is violet' 142 | >>> t = Templater() # default min_block_size = 1 143 | >>> t.learn(str_1) 144 | >>> t.learn(str_2) 145 | >>> print t._template 146 | [None, 'my favorite color is ', None, 'l', None, 'e', None] 147 | 148 | We don't want that ``'l'`` and ``'e'`` there, right? So:: 149 | 150 | >>> t = Templater(min_block_size=2) 151 | >>> t.learn(str_1) 152 | >>> t.learn(str_2) 153 | >>> print t._template 154 | [None, 'my favorite color is ', None] 155 | 156 | 157 | You can also add "headers" to your template - the headers will be the name of 158 | your markers, so you'll have a template with named markers and ``parse`` will 159 | return a ``dict`` instead of ``list``. It's more legible than using list 160 | indices, let's see:: 161 | 162 | >>> import re 163 | >>> # Let's create a regexp that cases with '{{var}}' (it'll be our marker) 164 | >>> regexp_marker = re.compile(r'{{([a-zA-Z0-9_-]*)}}') 165 | >>> template = Templater('{{first-var}}{{second-var}}{{third-var}}', 166 | marker=regexp_marker) 167 | >>> # The template knows the name of each marker just using the regexp provided 168 | >>> # Passing marker as regexp to specify named markers also work for Templater.open 169 | 170 | >>> print template.parse('This is a test.') 171 | {'second-var': ' is ', 'third-var': ' a test.', 'first-var': 'This '} 172 | 173 | >>> # To save the template with named markers we need to provide a Python string. 174 | >>> # Templater will call .format() of this string for each marker with its name 175 | >>> template.save('template-with-named-markers.html', marker='--{}--') 176 | >>> # Will save '--first-var----second-var----third-var--\n' 177 | 178 | And if you have a template without headers, just add to it with ``add_headers`` 179 | method:: 180 | 181 | >>> t = Templater('++++', marker='+') 182 | >>> t.parse('helloworld') 183 | ['', 'hello', 'world', ''] 184 | 185 | >>> t.add_headers(['before', 'first-column', 'second-column', 'after']) 186 | >>> t.parse('helloworld') 187 | {'after': '', 'before': '', 'first-column': 'hello', 'second-column': 'world'} 188 | 189 | **Note**: named markers have a problem: you can't run ``learn`` if you use them. 190 | 191 | 192 | Notes 193 | ----- 194 | 195 | I really want to know if you are using this project and what is your impression 196 | about it. If you have new ideas of features, discovered bugs or just want to 197 | say "thank you, I'm using it!", please contact me at 198 | `alvarojusten at gmail `_. 199 | 200 | If you want to code some stuff, 201 | just `fork it on GitHub `_ and create a 202 | pull request. Some technical notes for you: 203 | 204 | - This project uses `Test-Driven Development 205 | `_. 206 | 207 | - The tests are run using Python 2.7.2 on Ubuntu 11.10 amd64. 208 | - You can see the changes between versions in 209 | `CHANGELOG.rst `_. 210 | - This project uses `semantic versioning `_ (thanks, 211 | `Tom Preston-Werner `_). 212 | 213 | 214 | 215 | Author 216 | ------ 217 | 218 | This software is developed by 219 | `Álvaro Justen aka Turicas `_. 220 | 221 | Many thanks to `Adrian Holovaty `_ - he created 222 | `templatemaker `_, the project which 223 | ``templater`` was inspired in/forked from - and to 224 | `Escola de Matemática Aplicada (Fundação Getúlio Vargas) `_ 225 | which gives me interesting problems to solve. :-) 226 | 227 | 228 | License 229 | ------- 230 | 231 | `GPL version 2 `_ 232 | -------------------------------------------------------------------------------- /examples/change_min_block_size.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | # coding: utf-8 3 | 4 | from templater import Templater 5 | 6 | 7 | str_1 = 'my favorite color is blue' 8 | str_2 = 'my favorite color is violet' 9 | print 'Learning from:' 10 | print ' ', str_1 11 | print ' ', str_2 12 | 13 | t = Templater() # default min_block_size = 1 14 | t.learn(str_1) 15 | t.learn(str_2) 16 | print 'Template for min_block_size=1 (default):' 17 | print ' ', t._template 18 | 19 | t = Templater(min_block_size=2) 20 | t.learn(str_1) 21 | t.learn(str_2) 22 | print 'Template for min_block_size=2:' 23 | print ' ', t._template 24 | -------------------------------------------------------------------------------- /examples/named_markers.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | # coding: utf-8 3 | 4 | from re import compile as re_compile 5 | from templater import Templater 6 | 7 | 8 | regexp_marker = re_compile(r'{{([a-zA-Z0-9_-]*)}}') # match ''{{var}}'' 9 | template = Templater('{{first-var}}{{second-var}}{{third-var}}', 10 | marker=regexp_marker) 11 | # regexp marker also works for Templater.open to specify named markers 12 | result = template.parse('This is a test.') # returns a dict 13 | print result 14 | 15 | template.save('template-with-named-markers.html', marker='{{{{{}}}}}') 16 | -------------------------------------------------------------------------------- /examples/parsing_files.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | # coding: utf-8 3 | 4 | from time import time 5 | from glob import glob 6 | from templater import Templater 7 | 8 | 9 | files = glob('html/*.html') # You must have some .html files in html/ 10 | template = Templater() 11 | print 'Time to learn' 12 | start = time() 13 | for filename in files: 14 | print ' Learning "%s"...' % filename, 15 | fp = open(filename) 16 | template.learn(fp.read()) 17 | fp.close() 18 | print 'OK' 19 | end = time() 20 | print ' Time:', end - start 21 | 22 | print 'Template created:' 23 | print template._template 24 | 25 | print 'Now, work!' 26 | start = time() 27 | for filename in files: 28 | print ' Parsing "%s"...' % filename 29 | fp = open(filename) 30 | print ' Result:', template.parse(fp.read()) 31 | fp.close() 32 | end = time() 33 | print ' Time: ', end - start 34 | -------------------------------------------------------------------------------- /examples/pre_processed_template.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | # coding: utf-8 3 | 4 | from templater import Templater 5 | 6 | template = Templater(template=[None, '', None, '', None]) 7 | print template.join(['', 'Python rules', '']) # prints 'Python rules' 8 | -------------------------------------------------------------------------------- /examples/save_open_dump_load.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | # coding: utf-8 3 | 4 | from os import unlink 5 | from templater import Templater 6 | 7 | 8 | t = Templater() 9 | t.learn('spam') 10 | t.learn('eggs') 11 | t.learn('ham') 12 | t.save('my-little-template.html', marker='|||') # will put a `\n` in the EOF 13 | t.dump('my-template.tpl') 14 | print t.parse('parsing using first template object') 15 | 16 | t2 = Templater.open('my-little-template.html', marker='|||') 17 | # it removes `\n`/`\r\n` in the end of file before creating template definition 18 | print t2.parse('parsing using second template object') 19 | 20 | t3 = Templater.load('my-template.tpl') 21 | print t3.parse('parsing using third template object') 22 | 23 | # 'my-little-template.html' will have the template string with blanks filled by 24 | # '|||' 25 | # 'my-template.tpl' will have the pickle of Templater object 26 | 27 | # Removing files: 28 | unlink('my-little-template.html') 29 | unlink('my-template.tpl') 30 | -------------------------------------------------------------------------------- /examples/simple_example.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | # coding: utf-8 3 | 4 | from templater import Templater 5 | 6 | 7 | texts_to_learn = [' spam and eggs ', ' ham and spam ', 8 | ' white and black '] 9 | text_to_parse = texts_to_learn[-1] 10 | template = Templater() 11 | for text in texts_to_learn: 12 | print 'Learning "%s"...' % text 13 | template.learn(text) 14 | print 'Template created:', template._template 15 | print 'Parsing text "%s"...' % text_to_parse 16 | print ' Result:', template.parse(text_to_parse) 17 | print 'Filling the blanks:', template.join(['', 'yellow', 'blue', '']) 18 | -------------------------------------------------------------------------------- /examples/strings_with_markers_as_template.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | # coding: utf-8 3 | 4 | from templater import Templater 5 | 6 | 7 | template = Templater(template='||| and |||', marker='|||') 8 | print template.join(['', 'red', 'blue', '']) # prints 'red and blue' 9 | -------------------------------------------------------------------------------- /requirements/development.txt: -------------------------------------------------------------------------------- 1 | virtualenv 2 | virtualenvwrapper 3 | nose 4 | yanc 5 | coverage 6 | -------------------------------------------------------------------------------- /run-tests.sh: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | 3 | if [ -z "$VIRTUAL_ENV" ]; then 4 | echo 'Error: you should be in a virtualenv. Create it using:' 5 | echo ' mkvirtualenv --no-site-packages templater-env' 6 | echo 'You need to have virtualenv and virtualenvwrapper installed:' 7 | echo ' pip install virtualenv virtualenvwrapper' 8 | exit 1 9 | fi 10 | 11 | clear 12 | make clean build 13 | cp $(find build/ -name _templater.so) . 14 | $VIRTUAL_ENV/bin/python `which nosetests` -dv \ 15 | --with-coverage --cover-package templater --with-yanc 16 | -------------------------------------------------------------------------------- /setup.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | # coding: utf-8 3 | 4 | from distutils.core import setup, Extension 5 | 6 | 7 | setup(name='templater', 8 | version='0.4.0', 9 | description=('Extract template (a pattern) from strings and parse other' 10 | 'strings with this pattern.'), 11 | long_description=open('README.rst').read(), 12 | author=u'Álvaro Justen', 13 | author_email='alvarojusten@gmail.com', 14 | url='https://github.com/turicas/templater/', 15 | py_modules=['templater'], 16 | ext_modules=[Extension('_templater', ['templater.c'])], 17 | keywords=['template', 'reversed template', 'template making', 18 | 'wrapper induction'], 19 | classifiers = [ 20 | 'Development Status :: 3 - Alpha', 21 | 'Intended Audience :: Developers', 22 | 'Intended Audience :: Science/Research', 23 | 'License :: OSI Approved :: GNU General Public License (GPL)', 24 | 'Natural Language :: English', 25 | 'Operating System :: OS Independent', 26 | 'Programming Language :: Python :: 2.7', 27 | 'Topic :: Software Development :: Libraries :: Python Modules' 28 | ], 29 | ) 30 | -------------------------------------------------------------------------------- /templater.c: -------------------------------------------------------------------------------- 1 | #include 2 | 3 | /* 4 | Original code from: 5 | author='Adrian Holovaty', 6 | author_email='adrian@holovaty.com', 7 | http://templatemaker.googlecode.com/ 8 | 9 | longest_match() and longest_match_shifter() 10 | 11 | Returns the length of the longest common substring (LCS) in the strings 12 | a and b. 13 | 14 | Sets a_offset to the index of a where the LCS begins. 15 | Sets b_offset to the index of b where the LCS begins. 16 | 17 | If there is NO common substring, it returns 0 and sets both 18 | a_offset and b_offset to -1. 19 | 20 | The strings do not have to be equal length. 21 | 22 | The algorithm works by comparing one character at a time and "shifting" the 23 | strings so that different characters are compared. For example, given 24 | a="ABC" and b="DEF", picture these alignments: 25 | 26 | (Shift a to the right) 27 | ------------------------------------------------------- 28 | a | ABC ABC ABC 29 | b | DEF DEF DEF 30 | shift index | 0 1 2 31 | possible LCS | 3 2 1 32 | comparisons | AD, BE, CF AE, BF AF 33 | 34 | (Shift b to the right) 35 | ------------------------------------------------------- 36 | | ABC ABC ABC 37 | | DEF DEF DEF 38 | shift index | 0 1 2 39 | possible LCS | 3 2 1 40 | comparisons | AD, BE, CF BD, CE CD 41 | 42 | The algorithm short circuits based on the best_size found so far. For example, 43 | given a="ABC" and b="ABC", the first cycle of comparisons (AA, BB, CC) would 44 | result in a best_size=3. Because the algorithm starts with zero shift (i.e., 45 | it starts with the highest possible LCS) and adds 1 to the shift index each 46 | time through, it can safely exit without doing any more comparisons. 47 | 48 | This algorithm is O^(m + m-1 + m-2 + ... + 1 + n + n-1 + n-2 + ... + 1), where 49 | m and n are the length of the two strings. Due to short circuiting, the 50 | algorithm could potentially finish after the very 51 | first set of comparisons. The algorithm is slowest when the LCS is smallest, 52 | and the algorithm is fastest when the LCS is biggest. 53 | 54 | longest_match_shifter() performs "one side" of the shift -- e.g., "Shift a to 55 | the right" in the above illustration. longest_match() simply calls 56 | longest_match_shifter() twice, flipping the strings. 57 | */ 58 | 59 | int longest_match_shifter(char* a, char* b, int a_start, int a_end, int b_start, int b_end, int best_size, int* a_offset, int* b_offset) { 60 | int i, j, k; 61 | unsigned int current_size; 62 | 63 | for (i = b_start, current_size = 0; i < b_end; i++, current_size = 0) { // i is b starting index. 64 | if (best_size >= b_end - i) break; // Short-circuit. See comment above. 65 | for (j = i, k = a_start; k < a_end && j < b_end; j++, k++) { // k is index of a, j is index of b. 66 | if (a[k] == b[j]) { 67 | if (++current_size > best_size) { 68 | best_size = current_size; 69 | *a_offset = k - current_size + 1; 70 | *b_offset = j - current_size + 1; 71 | } 72 | } 73 | else { 74 | current_size = 0; 75 | } 76 | } 77 | } 78 | return best_size; 79 | } 80 | 81 | // a_offset and b_offset are relative to the *whole* string, not the substring 82 | // (as defined by a_start and a_end). 83 | // a_end and b_end are (the last index + 1). 84 | int longest_match(char* a, char* b, int a_start, int a_end, int b_start, int b_end, int* a_offset, int* b_offset) { 85 | unsigned int best_size; 86 | *a_offset = -1; 87 | *b_offset = -1; 88 | best_size = longest_match_shifter(a, b, a_start, a_end, b_start, b_end, 0, a_offset, b_offset); 89 | best_size = longest_match_shifter(b, a, b_start, b_end, a_start, a_end, best_size, b_offset, a_offset); 90 | return best_size; 91 | } 92 | 93 | static PyObject * function_longest_match(PyObject *self, PyObject *args) { 94 | char* a; 95 | char* b; 96 | int a_offset, b_offset, lena, lenb; 97 | unsigned int best_size; 98 | 99 | if (!PyArg_ParseTuple(args, "s#s#", &a, &lena, &b, &lenb)) 100 | return NULL; 101 | 102 | best_size = longest_match(a, b, 0, lena, 0, lenb, &a_offset, &b_offset); 103 | return Py_BuildValue("(iii)", best_size, a_offset, b_offset); 104 | } 105 | 106 | static PyMethodDef ModuleMethods[] = { 107 | {"longest_match", function_longest_match, METH_VARARGS, "Given two strings, determines the longest common substring and returns a tuple of (best_size, a_offset, b_offset)."}, 108 | {NULL, NULL, 0, NULL} // sentinel 109 | }; 110 | 111 | PyMODINIT_FUNC init_templater(void) { 112 | (void) Py_InitModule("_templater", ModuleMethods); 113 | } 114 | -------------------------------------------------------------------------------- /templater.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | # coding: utf-8 3 | 4 | from cPickle import dump as pickle_dump, load as pickle_load 5 | from re import compile as re_compile 6 | from _templater import longest_match as lcs 7 | 8 | 9 | type_regexp = type(re_compile('')) 10 | MARKER = '|||' 11 | NAMED_MARKER = '{{{{{}}}}}' # '{{sample-var}}' 12 | 13 | class Templater(object): 14 | def __init__(self, template=None, marker='|||', min_block_size=1): 15 | self._template = template 16 | self._min_block_size = min_block_size 17 | self._marker = marker 18 | self._headers = None 19 | self._named_markers = False 20 | if type(template) in (str, unicode): 21 | self._template, self._named_markers, self._headers = \ 22 | _create_template_from_string(template, marker) 23 | 24 | def learn(self, new_text): 25 | if self._named_markers: 26 | raise NotImplementedError("Actually you can't learn in a template " 27 | "with named markers") 28 | if self._template is None: 29 | text = new_text 30 | else: 31 | text = '\0\0\0'.join(filter(lambda x: x is not None, self._template)) 32 | self._template = _create_template(new_text, text, (0, len(new_text)), 33 | (0, len(text)), self._min_block_size) 34 | 35 | def parse(self, text): 36 | result = _parser(self._template, text) 37 | if self._named_markers: 38 | return dict(zip(self._headers, result)) 39 | else: 40 | return result 41 | 42 | def join(self, elements): 43 | elements_length = len(elements) 44 | variables_length = self._template.count(None) 45 | if elements_length != variables_length: 46 | error_msg = ("Wrong number of variables (passed: {}, expected: " 47 | "{})".format(elements_length, variables_length)) 48 | raise AttributeError(error_msg) 49 | text = self._template[:] 50 | variable_index = 0 51 | for index, element in enumerate(text): 52 | if element is None: 53 | text[index] = elements[variable_index] 54 | variable_index += 1 55 | return ''.join(text) 56 | 57 | def dump(self, filename): 58 | """Dump the template object to ``filename`` so you can re-use it later. 59 | 60 | This method uses cPickle to serialize internal template model, so you 61 | don't need to pass through the learn process everytime you need to 62 | parse data. It's worth using this method since learning process 63 | generally cost a lot of time compared to parsing. 64 | """ 65 | fp = open(filename, 'w') 66 | pickle_dump(self, fp) 67 | fp.close() 68 | 69 | @staticmethod 70 | def load(filename): 71 | """Load a template from ``filename``, return ``Templater`` object. 72 | 73 | This method must be used in pair with ``Templater.dump`` - it loads 74 | the template definition from a file using cPickle, creates a 75 | ``Templater`` object with the definition and returns it. 76 | """ 77 | fp = open(filename) 78 | processed_template = pickle_load(fp) 79 | fp.close() 80 | return processed_template 81 | 82 | def save(self, filename, marker=None, headers=None): 83 | """Save the template to ``filename`` using ``marker`` as marker. 84 | 85 | This method looks like ``Templater.dump``, the difference is that it 86 | does not save/pickle the entire ``Templater`` object - it uses 87 | ``Templater.join`` to fill the blanks with ``marker`` and then save the 88 | resulting string to ``filename``. 89 | It should be used in pair with ``Templater.open``. 90 | """ 91 | if not self._named_markers: 92 | if marker is None: 93 | marker = self._marker 94 | blanks = [marker] * self._template.count(None) 95 | else: 96 | if headers is not None and len(headers) != len(self._headers): 97 | raise AttributeError('Incorrect number of headers (passed:' 98 | ' {}, expected: {})'.format( 99 | len(headers), len(self._headers))) 100 | if marker is None: 101 | marker = NAMED_MARKER 102 | if headers is None: 103 | headers = self._headers 104 | blanks = [marker.format(header) for header in headers] 105 | fp = open(filename, 'w') 106 | fp.write(self.join(blanks) + '\n') 107 | fp.close() 108 | 109 | @staticmethod 110 | def open(filename, marker=MARKER): 111 | """Open ``filename``, split in ``marker``, return ``Templater`` object. 112 | 113 | You should use this method in pair with ``Templater.save`` or if you 114 | want to write the templates with your own hands. It works similar to 115 | ``Templater.load``, except by the fact that ``load`` saves the entire 116 | ``Templater`` object and ``open`` saves only the template string, 117 | filling the blanks with ``marker``. 118 | """ 119 | fp = open(filename) 120 | contents = fp.read() 121 | fp.close() 122 | if contents[-2:] == '\r\n': 123 | contents = contents[:-2] 124 | elif contents[-1] == '\n': 125 | contents = contents[:-1] 126 | template = Templater(template=contents, marker=marker) 127 | return template 128 | 129 | def add_headers(self, headers): 130 | """Add/modifiy headers (names of markers) to a template.""" 131 | if len(headers) != self._template.count(None): 132 | raise ValueError("Wrong number of headers (passed: {}, expected: " 133 | "{})".format(len(headers), self._template.count(None))) 134 | self._named_markers = True 135 | self._headers = headers 136 | 137 | def parse_file(self, filename): 138 | """Open, read a file and call ``Templater.parse`` with its contents. 139 | 140 | If the file ends with ``\n`` or ``\r\n``, it'll be removed. 141 | """ 142 | fp = open(filename) 143 | contents = fp.read() 144 | fp.close() 145 | if contents[-2:] == '\r\n': 146 | contents = contents[:-2] 147 | elif contents[-1] == '\n': 148 | contents = contents[:-1] 149 | return self.parse(contents) 150 | 151 | 152 | def _parser(template, text): 153 | result = [] 154 | text_index = 0 155 | last_element_index = len(template) - 1 156 | for index, element in enumerate(template): 157 | if element is None: 158 | if index != last_element_index: 159 | new_index = text.index(template[index + 1], text_index) 160 | else: 161 | new_index = None 162 | result.append(text[text_index:new_index]) 163 | text_index = new_index 164 | else: 165 | element_length = len(element) 166 | assert text[text_index:text_index + element_length] == element 167 | text_index += element_length 168 | return result 169 | 170 | def _create_template(str_1, str_2, (start_1, end_1), (start_2, end_2), 171 | min_block_size=1): 172 | lcs_size, lcs_1_start, lcs_2_start = lcs(str_1[start_1:end_1], 173 | str_2[start_2:end_2]) 174 | if lcs_size < min_block_size: 175 | return [None] 176 | else: 177 | common = str_1[start_1 + lcs_1_start:start_1 + lcs_1_start + lcs_size] 178 | return _create_template(str_1, str_2, 179 | (start_1, start_1 + lcs_1_start), 180 | (start_2, start_2 + lcs_2_start), 181 | min_block_size) + \ 182 | [str_1[start_1 + lcs_1_start:start_1 + lcs_1_start + lcs_size]] + \ 183 | _create_template(str_1, str_2, 184 | (start_1 + lcs_1_start + lcs_size, end_1), 185 | (start_2 + lcs_2_start + lcs_size, end_2), 186 | min_block_size) 187 | 188 | def _create_template_from_string(text, marker): 189 | named_markers = type(marker) == type_regexp 190 | if named_markers: 191 | results = marker.split(text) 192 | tokens, headers = [x for x in results[::2] if x], results[1::2] 193 | else: 194 | tokens = [x for x in text.split(marker) if x != ''] 195 | template = list(sum(zip([None] * len(tokens), tokens), ())) + [None] 196 | if named_markers: 197 | if template.count(None) != len(headers): 198 | raise ValueError("Template error! Verify if markers are separated" 199 | " at least by one character") 200 | return template, True, headers 201 | return template, False, None 202 | -------------------------------------------------------------------------------- /tests/test_Templater.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | # coding: utf-8 3 | 4 | from os import unlink 5 | from re import compile as re_compile 6 | from templater import Templater, MARKER, NAMED_MARKER 7 | 8 | 9 | regexp_marker = re_compile(r'{{([a-zA-Z0-9_-]*)}}') 10 | 11 | def read_file_and_delete(filename): 12 | fp = open(filename) 13 | contents = fp.read() 14 | fp.close() 15 | unlink(filename) 16 | return contents 17 | 18 | def write_file(filename, contents): 19 | fp = open(filename, 'w') 20 | fp.write(contents) 21 | fp.close() 22 | 23 | def test_new_learn_text_trying_to_delete_some_variable(): 24 | template = Templater() 25 | template.learn(' a and b ') 26 | template.learn(' c and d ') 27 | template.learn(' e and ') 28 | result = template._template 29 | expected = [None, ' ', None, ' and ', None, ' ', None] 30 | assert result == expected 31 | 32 | def test_parse_should_return_a_list_with_the_blanks_contents(): 33 | template = Templater() 34 | template.learn('a b d') 35 | template.learn('a e d') 36 | result = template.parse('a b c d') 37 | expected = ['', 'b c', ''] 38 | assert result == expected 39 | 40 | def test_Templater_parse_file_should_open_and_parse_a_file_from_filename(): 41 | template = Templater('+++', marker='+') 42 | fp = open('test.html', 'w') 43 | fp.write('testing parsing files\n') 44 | fp.close() 45 | result_1 = template.parse_file('test.html') 46 | expected = ['testing ', ' parsing ', ' files'] 47 | unlink('test.html') 48 | assert expected == result_1 49 | 50 | fp = open('test.html', 'w') 51 | fp.write('testing parsing files\r\n') 52 | fp.close() 53 | result_2 = template.parse_file('test.html') 54 | unlink('test.html') 55 | assert expected == result_2 56 | 57 | def test_join_should_fill_the_blanks_with_elements_received(): 58 | template = Templater() 59 | template.learn('a b d') 60 | template.learn('a e d') 61 | parsed = template.parse('a b c d') 62 | result = template.join(parsed) 63 | expected = 'a b c d' 64 | assert result == expected 65 | 66 | def test_join_with_less_parameters_than_variables_should_raise_AttributeError(): 67 | template = Templater() 68 | template.learn('a b d') 69 | template.learn('a e d') 70 | try: 71 | result = template.join(['']) 72 | except AttributeError: 73 | pass 74 | else: 75 | assert 'AttributeError not raised!' == False 76 | 77 | def test_Templater_should_optionally_import_pre_processed_template(): 78 | pre_processed = [None, '', None, '', None] 79 | template = Templater(template=pre_processed) 80 | assert template._template == pre_processed 81 | assert template.join(['', 'python', '']) == 'python' 82 | 83 | def test_Templater_should_optionally_import_template_as_string_with_marks(): 84 | template = Templater(template='|||', marker='|||') 85 | result_template = template._template 86 | assert result_template == [None, '', None, '', None] 87 | assert template.join(['', 'spam eggs', '']) == 'spam eggs' 88 | 89 | def test_Templater_dump_and_load_should_pickle_and_unpickle(): 90 | processed_template = [None, '', None, '', None, '', None] 91 | template = Templater(template=processed_template, min_block_size=6) 92 | template.dump('my-template.tpl') 93 | t2 = Templater.load('my-template.tpl') 94 | unlink('my-template.tpl') 95 | result_1 = t2._template 96 | expected_1 = processed_template 97 | result_2 = t2._min_block_size 98 | expected_2 = 6 99 | assert expected_1 == result_1 100 | assert expected_2 == result_2 101 | 102 | def test_should_be_able_to_adjust_minimum_size_of_a_block(): 103 | t = Templater(min_block_size=2) 104 | t.learn('git and pyth') 105 | t.learn('eggs and spam') 106 | expected = [None, ' and ', None] 107 | result = t._template 108 | assert expected == result 109 | 110 | def test_Templater_save_should_save_template_as_a_raw_file_with_markers(): 111 | processed_template = [None, '', None, '', None, '', None] 112 | t = Templater(template=processed_template) 113 | t.save('test.html', marker='|||') 114 | result = read_file_and_delete('test.html') 115 | expected = '||||||||||||\n' 116 | assert expected == result 117 | 118 | def test_Templater_should_accept_named_markers_in_init(): 119 | template = '{{start}}{{middle}}{{end}}' 120 | t = Templater(template=template, marker=regexp_marker) 121 | result_1 = t._template 122 | expected_1 = [None, '', None, '', None] 123 | assert expected_1 == result_1 124 | 125 | result_2 = t._headers 126 | expected_2 = ['start', 'middle', 'end'] 127 | assert expected_2 == result_2 128 | 129 | def test_Templater_open_should_load_template_from_a_raw_file_with_markers(): 130 | write_file('test.html', '||||||||||||') 131 | t = Templater.open('test.html', marker='|||') 132 | unlink('test.html') 133 | result = t._template 134 | expected = [None, '', None, '', None, '', None] 135 | assert expected == result 136 | 137 | def test_Templater_open_should_remove_leading_linefeed_if_there_is_some(): 138 | fp = open('test.html', 'w') 139 | fp.write('||||||||||||\n') 140 | fp.close() 141 | t = Templater.open('test.html', marker='|||') 142 | unlink('test.html') 143 | result_1 = t._template 144 | expected = [None, '', None, '', None, '', None] 145 | assert expected == result_1 146 | 147 | fp = open('test.html', 'w') 148 | fp.write('||||||||||||\r\n') 149 | fp.close() 150 | t = Templater.open('test.html', marker='|||') 151 | unlink('test.html') 152 | result_2 = t._template 153 | assert expected == result_2 154 | 155 | def test_named_markers_should_work(): 156 | write_file('test.html', 157 | '|||[first]|||[second]|||[third]|||[fourth]') 158 | t = Templater.open('test.html', marker=re_compile(r'\|\|\|\[([^\]]+)\]')) 159 | unlink('test.html') 160 | result_1 = t._template 161 | expected_1 = [None, '', None, '', None, '', None] 162 | assert result_1 == expected_1 163 | 164 | result_2 = t.parse('helloworld') 165 | expected_2 = {'first': '', 'second': 'hello', 'third': 'world', 166 | 'fourth': ''} 167 | assert expected_2 == result_2 168 | 169 | def test_should_not_have_named_marks_without_nothing_in_the_middle(): 170 | write_file('test.html', '{{first}}{{second}}{{text}}{{last}}') 171 | try: 172 | t = Templater.open('test.html', marker=regexp_marker) 173 | except ValueError: 174 | pass 175 | else: 176 | assert "ValueError not raised!" == False 177 | 178 | def test_if_there_are_no_named_marker_in_the_start_of_template(): 179 | write_file('test.html', '{{text}}{{end}}') 180 | try: 181 | t = Templater.open('test.html', marker=regexp_marker) 182 | except ValueError: 183 | unlink('test.html') 184 | else: 185 | unlink('test.html') 186 | assert "ValueError not raised!" == False 187 | 188 | def test_raise_ValueError_if_there_is_no_named_marker_in_the_end_of_template(): 189 | write_file('test.html', '{{start}}{{text}}') 190 | try: 191 | t = Templater.open('test.html', marker=regexp_marker) 192 | except ValueError: 193 | unlink('test.html') 194 | else: 195 | unlink('test.html') 196 | assert "ValueError not raised!" == False 197 | 198 | # SAVE: marker + headers cases: 199 | # marker | self._named_markers | result 200 | # NO | NO | self._marker / ignore headers 201 | # NO | YES | NAMED_MARKER / headers or self._headers 202 | # YES | NO | marker / ignore headers 203 | # YES | YES | marker.format() / headers or self._headers 204 | 205 | def test_save_should_use_self_marker_if_no_marker_supplied(): 206 | t = Templater(template='+++', marker='+') 207 | t.save('test.html') 208 | result = read_file_and_delete('test.html') 209 | expected = '+++\n' 210 | assert expected == result 211 | 212 | def test_save_should_use_NAMED_MARKER_if_template_has_named_markers_and_no_marker_supplied(): 213 | t = Templater(template='{{one}}{{two}}{{three}}', 214 | marker=regexp_marker) 215 | t.save('test.html') 216 | result = read_file_and_delete('test.html') 217 | named_markers = [NAMED_MARKER.format(header) for header in t._headers] 218 | expected = t.join(named_markers) + '\n' 219 | assert expected == result 220 | 221 | def test_save_should_use_marker_if_supplied_and_template_hasnt_named_markers(): 222 | t = Templater(template='+++', marker='+') 223 | t.save('test.html', marker='%%') 224 | result = read_file_and_delete('test.html') 225 | expected = '%%%%%%\n' 226 | assert expected == result 227 | 228 | def test_save_should_use_python_format_if_marker_is_supplied_and_template_has_named_markers(): 229 | t = Templater(template='{{start}}{{text}}{{end}}', 230 | marker=regexp_marker) 231 | t.save('test.html', marker='[--{}--]') 232 | result = read_file_and_delete('test.html') 233 | expected = '[--start--][--text--][--end--]\n' 234 | assert expected == result 235 | 236 | def test_save_should_use_headers_instead_of_self_headers_if_supplied(): 237 | t = Templater(template='{{one}}{{two}}{{three}}', 238 | marker=regexp_marker) 239 | t.save('test.html', headers=list('abc')) 240 | result_1 = read_file_and_delete('test.html') 241 | named_markers = [NAMED_MARKER.format(header) for header in list('abc')] 242 | expected_1 = t.join(named_markers) + '\n' 243 | assert expected_1 == result_1 244 | 245 | t.save('test.html', marker='[--{}--]', headers=list('abc')) 246 | result_2 = read_file_and_delete('test.html') 247 | expected_2 = '[--a--][--b--][--c--]' + '\n' 248 | assert expected_2 == result_2 249 | 250 | def test_passing_headers_with_different_size_from_self_headers_should_raise_AttributeError(): 251 | t = Templater(template='{{one}}{{two}}{{three}}', 252 | marker=regexp_marker) 253 | try: 254 | t.save('test.html', headers=list('abcde')) 255 | except AttributeError: 256 | pass 257 | else: 258 | unlink('test.html') 259 | raise 'AttributeError not raised!' 260 | 261 | def test_template_with_named_markers_should_not_be_able_to_learn(): 262 | t = Templater(template='{{one}}{{two}}{{three}}', 263 | marker=regexp_marker) 264 | try: 265 | t.learn('abc') 266 | except NotImplementedError: 267 | pass 268 | else: 269 | print t._template 270 | assert 'NotImplementedError not raised' == False 271 | 272 | def test_should_be_able_to_add_headers_to_a_template_without_named_markers(): 273 | t = Templater(template='|||||||||', marker='|||') 274 | t.add_headers(['one', 'two', 'three']) 275 | result = t.parse('abc') 276 | expected = {'one': 'a', 'two': 'b', 'three': 'c'} 277 | assert result == expected 278 | 279 | def test_add_headers_should_raise_ValueError_if_number_of_blanks_differ_from_number_of_headers(): 280 | t = Templater(template='|||||||||', marker='|||') 281 | try: 282 | t.add_headers(['one', 'two', 'three', 'four']) 283 | except ValueError: 284 | pass 285 | else: 286 | assert 'ValueError not raised!' == False 287 | -------------------------------------------------------------------------------- /tests/test_create_template.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | # coding: utf-8 3 | 4 | from templater import _create_template 5 | 6 | 7 | def test_different_strings_should_return_one_blank(): 8 | str_1 = '1' 9 | str_2 = '2' 10 | result = _create_template(str_1, str_2, (0, len(str_1)), (0, len(str_2))) 11 | expected = [None] 12 | assert result == expected 13 | 14 | def test_equal_strings_should_return_one_block(): 15 | str_1 = ' asd ' 16 | str_2 = ' asd ' 17 | result = _create_template(str_1, str_2, (0, len(str_1)), (0, len(str_2))) 18 | expected = [None, ' asd ', None] 19 | assert result == expected 20 | 21 | def test_different_strings_with_same_size(): 22 | str_1 = 'a1' 23 | str_2 = 'a2' 24 | result_1 = _create_template(str_1, str_2, (0, len(str_1)), (0, len(str_2))) 25 | expected_1 = [None, 'a', None] 26 | assert result_1 == expected_1 27 | 28 | str_1 = '1a' 29 | str_2 = '2a' 30 | result_2 = _create_template(str_1, str_2, (0, len(str_1)), (0, len(str_2))) 31 | expected_2 = [None, 'a', None] 32 | assert result_2 == expected_2 33 | 34 | str_1 = ' asd ' 35 | str_2 = ' qwe ' 36 | result_3 = _create_template(str_1, str_2, (0, len(str_1)), (0, len(str_2))) 37 | expected_3 = [None, ' ', None, ' ', None] 38 | assert result_3 == expected_3 39 | 40 | def test_different_strings_with_different_size(): 41 | str_1 = ' asd ' 42 | str_2 = ' qwe123 ' 43 | result = _create_template(str_1, str_2, (0, len(str_1)), (0, len(str_2))) 44 | expected = [None, ' ', None, ' ', None] 45 | assert result == expected 46 | 47 | def test_different_strings_with_one_of_size_zero(): 48 | str_1 = ' asd ' 49 | str_2 = ' ' 50 | result = _create_template(str_1, str_2, (0, len(str_1)), (0, len(str_2))) 51 | expected = [None, ' ', None, ' ', None] 52 | assert result == expected 53 | 54 | def test_more_than_one_variable_with_same_size(): 55 | str_1 = ' asd 123 ' 56 | str_2 = ' qwe 456 ' 57 | result = _create_template(str_1, str_2, (0, len(str_1)), (0, len(str_2))) 58 | expected = [None, ' ', None, ' ', None, ' ', None] 59 | assert result == expected 60 | 61 | def test_more_than_one_variable_with_different_sizes(): 62 | str_1 = ' asdfgh 123 ' 63 | str_2 = ' qwe 456qwe ' 64 | result = _create_template(str_1, str_2, (0, len(str_1)), (0, len(str_2))) 65 | expected = [None, ' ', None, ' ', None, ' ', None] 66 | assert result == expected 67 | 68 | def test_min_block_size(): 69 | str_1 = 'my favorite color is blue' 70 | str_2 = 'my favorite color is violet' 71 | result = _create_template(str_1, str_2, (0, len(str_1)), (0, len(str_2)), 72 | min_block_size=1) 73 | expected = [None, 'my favorite color is ', None, 'l', None, 'e', None] 74 | assert result == expected 75 | 76 | result = _create_template(str_1, str_2, (0, len(str_1)), (0, len(str_2)), 77 | min_block_size=2) 78 | expected = [None, 'my favorite color is ', None] 79 | assert result == expected 80 | -------------------------------------------------------------------------------- /tests/test_parser.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | # coding: utf-8 3 | 4 | from templater import _parser 5 | 6 | 7 | def test_parsing_template_with_one_blank(): 8 | text = ' testing ' 9 | template = [None] 10 | result = _parser(template, text) 11 | expected = [text] 12 | assert result == expected 13 | 14 | def test_parsing_template_with_three_blanks(): 15 | text = ' testing ' 16 | template = [None, ' ', None, ' ', None] 17 | result = _parser(template, text) 18 | expected = ['', 'testing', ''] 19 | assert result == expected 20 | 21 | def test_parsing_four_blanks(): 22 | text = ' testing and programming ' 23 | template = [None, ' ', None, ' and ', None, ' ', None] 24 | result = _parser(template, text) 25 | expected = ['', 'testing', 'programming', ''] 26 | assert result == expected 27 | 28 | def test_parsing_non_parseable_text_should_raise_ValueError(): 29 | text = ' testing programming ' 30 | template = [' ', None, ' and ', None, ' '] 31 | try: 32 | result = _parser(template, text) 33 | except ValueError: 34 | pass 35 | else: 36 | assert 'ValueError not raised!' == False 37 | 38 | def test_parsing_last_blank(): 39 | text = ' testing and programming blah' 40 | template = [None, ' ', None, ' and ', None, ' ', None] 41 | result = _parser(template, text) 42 | expected = ['', 'testing', 'programming', 'blah'] 43 | assert result == expected 44 | 45 | def test_parsing_first_blank(): 46 | text = 'blah testing and programming ' 47 | template = [None, ' ', None, ' and ', None, ' ', None] 48 | result = _parser(template, text) 49 | expected = ['blah', 'testing', 'programming', ''] 50 | assert result == expected 51 | --------------------------------------------------------------------------------