├── formula.png ├── README.md ├── ReadCsv.py ├── PngToJPGConverter ├── MathPixAPI ├── .gitignore ├── RenderAndSaveQuestion └── LICENSE /formula.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/lingarajsankaravelu/LatexToImageConverter/master/formula.png -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | ##### LatexToImageConverter 2 | ##### Data Cleaning and Image format Conversion. 3 | 1. Read Data from CSV and write it to local mongoCollection. 4 | 2. Converts an Image from png to jpeg from the given source to destination directory 5 | 6 | ##### LatexToImage Conversion 7 | 1. Render given text(latex and normal text) and save as png. 8 | 4. Upload Rendered Image to MathPix API and read their response synchronously. 9 | -------------------------------------------------------------------------------- /ReadCsv.py: -------------------------------------------------------------------------------- 1 | import pymongo 2 | import csv as csv_reader 3 | mongo_connection = pymongo.MongoClient("mongodb://localhost") 4 | db = mongo_connection.mathpix 5 | 6 | #Reads CSV file from Local disk 7 | def readCsvFile(): 8 | with open('/Users/lingaraj/Desktop/questions_info_search.csv') as csv_file: 9 | row_count = 0 10 | read_csv = csv_reader.reader(csv_file,delimiter=',') 11 | db.drop_collection('questions') 12 | for row in read_csv: 13 | row_count = row_count + 1 14 | writeToCollection(row) 15 | print("Data Count:",row_count) 16 | pass 17 | 18 | def writeToCollection(row): 19 | record = {'questionId':row[0],'questionText':row[1]} 20 | db.questions.insert_one(record) 21 | pass 22 | if __name__ == '__main__': 23 | readCsvFile() -------------------------------------------------------------------------------- /PngToJPGConverter: -------------------------------------------------------------------------------- 1 | from PIL import Image 2 | from os import listdir 3 | from os.path import splitext 4 | target = '.jpg' 5 | source = '.png' 6 | size = 10,10 7 | sourceDirectory = '/Users/lingaraj/Desktop/questionRenders/' 8 | targetDirectory = '/Users/lingaraj/Desktop/questionRendersJPeg/' 9 | 10 | #Converts PNG to JPEG from respective source to destination directory 11 | def convertPngToJPEG(): 12 | for file in listdir(sourceDirectory): 13 | filename, extension = splitext(file) 14 | try: 15 | if extension == source: 16 | im = Image.open(sourceDirectory+filename+extension) 17 | im = im.convert("RGB") 18 | #im.thumbnail(size,Image.ANTIALIAS) 19 | im.save(targetDirectory+filename + target) 20 | print('Convert success:', filename) 21 | except OSError: 22 | print('Cannot convert %s' % file) 23 | pass 24 | if __name__ == '__main__': 25 | convertPngToJPEG() -------------------------------------------------------------------------------- /MathPixAPI: -------------------------------------------------------------------------------- 1 | import requests 2 | import sys 3 | import base64 4 | import requests 5 | import json 6 | import pymongo 7 | from os.path import splitext 8 | from os import listdir 9 | targetextension = '.jpg' 10 | base_url ='https://api.mathpix.com/v3/latex' 11 | targetDirectory = '/Users/lingaraj/Desktop/questionRendersJPeg/' 12 | mongo_connection = pymongo.MongoClient("mongodb://localhost") 13 | db = mongo_connection.mathpix 14 | questions = db['questions'] 15 | static_file_name = '5a4f5b65bb6527ab61aa6bcc' 16 | 17 | # Makes Synchronous request to MathPixAPI with the images one by one and updated mongoDB 18 | def contactMathPix(fileName): 19 | print('Math Pix Request created for',fileName) 20 | file_path = targetDirectory+fileName+targetextension 21 | image_uri = "data:image/jpg;base64," + base64.b64encode(open(file_path, "rb").read()) 22 | request = requests.post(base_url, 23 | data=json.dumps({'src': image_uri,'ocr':['math','text'], 24 | 'formats': ['latex_normal', 'latex_styled']}), 25 | headers={"app_id": "mathpix", "app_key": "139ee4b61be2e4abcfb1238d9eb99902", 26 | "Content-type": "application/json"}) 27 | respons_dict = json.loads(request.text) 28 | json_dump = json.dumps(json.loads(request.text), indent=4, sort_keys=True) 29 | print(json_dump) 30 | pass 31 | 32 | 33 | def readDirectory(): 34 | count = 0 35 | for file in listdir(targetDirectory): 36 | filename, extension = splitext(file) 37 | if extension==targetextension: 38 | cursor = questions.find_one({'questionId':filename}) 39 | if cursor is None: 40 | print("UnResolved QuestionId:",filename) 41 | else: 42 | if filename==static_file_name: 43 | contactMathPix(filename) 44 | count = count + 1 45 | 46 | pass 47 | 48 | if __name__ == '__main__': 49 | readDirectory() 50 | -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- 1 | led / optimized / DLL files 2 | __pycache__/ 3 | *.py[cod] 4 | *$py.class 5 | 6 | # C extensions 7 | *.so 8 | 9 | # Distribution / packaging 10 | .Python 11 | build/ 12 | develop-eggs/ 13 | dist/ 14 | downloads/ 15 | eggs/ 16 | .eggs/ 17 | lib/ 18 | lib64/ 19 | parts/ 20 | sdist/ 21 | var/ 22 | wheels/ 23 | share/python-wheels/ 24 | *.egg-info/ 25 | .installed.cfg 26 | *.egg 27 | MANIFEST 28 | 29 | # PyInstaller 30 | # Usually these files are written by a python script from a template 31 | # before PyInstaller builds the exe, so as to inject date/other infos into it. 32 | *.manifest 33 | *.spec 34 | 35 | # Installer logs 36 | pip-log.txt 37 | pip-delete-this-directory.txt 38 | 39 | # Unit test / coverage reports 40 | htmlcov/ 41 | .tox/ 42 | .nox/ 43 | .coverage 44 | .coverage.* 45 | .cache 46 | nosetests.xml 47 | coverage.xml 48 | *.cover 49 | .hypothesis/ 50 | .pytest_cache/ 51 | 52 | # Translations 53 | *.mo 54 | *.pot 55 | 56 | # Django stuff: 57 | *.log 58 | local_settings.py 59 | db.sqlite3 60 | 61 | # Flask stuff: 62 | instance/ 63 | .webassets-cache 64 | 65 | # Scrapy stuff: 66 | .scrapy 67 | 68 | # Sphinx documentation 69 | docs/_build/ 70 | 71 | # PyBuilder 72 | target/ 73 | 74 | # Jupyter Notebook 75 | .ipynb_checkpoints 76 | 77 | # IPython 78 | profile_default/ 79 | ipython_config.py 80 | 81 | # pyenv 82 | .python-version 83 | 84 | # celery beat schedule file 85 | celerybeat-schedule 86 | 87 | # SageMath parsed files 88 | *.sage.py 89 | 90 | # Environments 91 | .env 92 | .venv 93 | ./venv/ 94 | env/ 95 | venv/ 96 | ENV/ 97 | env.bak/ 98 | venv.bak/ 99 | 100 | # Spyder project settings 101 | .spyderproject 102 | .spyproject 103 | 104 | # Rope project settings 105 | .ropeproject 106 | 107 | # mkdocs documentation 108 | /site 109 | 110 | # mypy 111 | .mypy_cache/ 112 | .dmypy.json 113 | dmypy.json 114 | 115 | # Pyre type checker 116 | .pyre/ 117 | 118 | # pycharm defaults 119 | .idea/ 120 | -------------------------------------------------------------------------------- /RenderAndSaveQuestion: -------------------------------------------------------------------------------- 1 | from __future__ import (absolute_import, division, print_function, 2 | unicode_literals) 3 | import pymongo 4 | import matplotlib 5 | matplotlib.use('TkAgg') 6 | import pylab 7 | import matplotlib.pyplot as plt 8 | mongo_connection = pymongo.MongoClient("mongodb://localhost") 9 | db = mongo_connection.mathpix 10 | questions = db['questions'] 11 | errors =db['errors'] 12 | direcotry = '/Users/lingaraj/Desktop/questionRenders/' 13 | 14 | #questionText -> A combination of latex and questiontext which needs to be converted and saved as an Image 15 | def renderAndSaveFileUsingPyLab(questionId,questionText): 16 | fig = pylab.figure() 17 | text = fig.text(0, 0, questionText) 18 | 19 | # Saving the figure will render the text. 20 | dpi = 300 21 | fig.savefig('formula.png', dpi=dpi) 22 | 23 | # Now we can work with text's bounding box. 24 | bbox = text.get_window_extent() 25 | width, height = bbox.size / float(dpi) + 0.005 26 | # Adjust the figure size so it can hold the entire text. 27 | fig.set_size_inches((width, height)) 28 | 29 | # Adjust text's vertical position. 30 | dy = (bbox.ymin / float(dpi)) / height 31 | text.set_position((0, -dy)) 32 | 33 | # Save the adjusted text. 34 | fig.savefig(direcotry+questionId+'.png', dpi=dpi) 35 | pass 36 | 37 | 38 | def renderAndSaveFile(questionId,questionText): 39 | plt.title(questionText,fontsize=20) 40 | #plt.text(questionText) 41 | plt.box(on=False) 42 | #plt.text(10, 10, questionText, fontsize=8) 43 | ax = plt.gca() 44 | ax.axes.get_xaxis().set_visible(False) 45 | ax.axes.get_yaxis().set_visible(False) 46 | plt.draw() 47 | plt.savefig(direcotry+questionId+'.png',dpi=900) 48 | pass 49 | 50 | 51 | def updateError(question_id): 52 | try: 53 | cursor = errors.find_one({'questionId',question_id}) 54 | if cursor is None: 55 | errors.insert_one({'questionId',question_id}) 56 | print('Question Id marked as error:',question_id) 57 | except Exception as e: 58 | print('problem inserting errors',type(e),e) 59 | pass 60 | 61 | 62 | def readAndRenderQuestionsCollection(): 63 | try: 64 | cursor = questions.find({}) 65 | errorIds = [] 66 | count = 1 67 | for doc in cursor: 68 | print ('processing record',count) 69 | question_id = doc['questionId'] 70 | try: 71 | question_text = doc['questionText'] 72 | renderAndSaveFileUsingPyLab(question_id,question_text) 73 | except Exception as e: 74 | updateError(question_id) 75 | errorIds.append(question_id) 76 | print('Problem with Question Text',type(e),e) 77 | 78 | #renderAndSaveFile(question_id,question_text) 79 | count = count + 1 80 | except Exception as e: 81 | print('Error reading data from collection:',type(e),e) 82 | pass 83 | 84 | if __name__ == '__main__': 85 | readAndRenderQuestionsCollection() 86 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | Apache License 2 | Version 2.0, January 2004 3 | http://www.apache.org/licenses/ 4 | 5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 6 | 7 | 1. Definitions. 8 | 9 | "License" shall mean the terms and conditions for use, reproduction, 10 | and distribution as defined by Sections 1 through 9 of this document. 11 | 12 | "Licensor" shall mean the copyright owner or entity authorized by 13 | the copyright owner that is granting the License. 14 | 15 | "Legal Entity" shall mean the union of the acting entity and all 16 | other entities that control, are controlled by, or are under common 17 | control with that entity. For the purposes of this definition, 18 | "control" means (i) the power, direct or indirect, to cause the 19 | direction or management of such entity, whether by contract or 20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 21 | outstanding shares, or (iii) beneficial ownership of such entity. 22 | 23 | "You" (or "Your") shall mean an individual or Legal Entity 24 | exercising permissions granted by this License. 25 | 26 | "Source" form shall mean the preferred form for making modifications, 27 | including but not limited to software source code, documentation 28 | source, and configuration files. 29 | 30 | "Object" form shall mean any form resulting from mechanical 31 | transformation or translation of a Source form, including but 32 | not limited to compiled object code, generated documentation, 33 | and conversions to other media types. 34 | 35 | "Work" shall mean the work of authorship, whether in Source or 36 | Object form, made available under the License, as indicated by a 37 | copyright notice that is included in or attached to the work 38 | (an example is provided in the Appendix below). 39 | 40 | "Derivative Works" shall mean any work, whether in Source or Object 41 | form, that is based on (or derived from) the Work and for which the 42 | editorial revisions, annotations, elaborations, or other modifications 43 | represent, as a whole, an original work of authorship. For the purposes 44 | of this License, Derivative Works shall not include works that remain 45 | separable from, or merely link (or bind by name) to the interfaces of, 46 | the Work and Derivative Works thereof. 47 | 48 | "Contribution" shall mean any work of authorship, including 49 | the original version of the Work and any modifications or additions 50 | to that Work or Derivative Works thereof, that is intentionally 51 | submitted to Licensor for inclusion in the Work by the copyright owner 52 | or by an individual or Legal Entity authorized to submit on behalf of 53 | the copyright owner. For the purposes of this definition, "submitted" 54 | means any form of electronic, verbal, or written communication sent 55 | to the Licensor or its representatives, including but not limited to 56 | communication on electronic mailing lists, source code control systems, 57 | and issue tracking systems that are managed by, or on behalf of, the 58 | Licensor for the purpose of discussing and improving the Work, but 59 | excluding communication that is conspicuously marked or otherwise 60 | designated in writing by the copyright owner as "Not a Contribution." 61 | 62 | "Contributor" shall mean Licensor and any individual or Legal Entity 63 | on behalf of whom a Contribution has been received by Licensor and 64 | subsequently incorporated within the Work. 65 | 66 | 2. Grant of Copyright License. Subject to the terms and conditions of 67 | this License, each Contributor hereby grants to You a perpetual, 68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 69 | copyright license to reproduce, prepare Derivative Works of, 70 | publicly display, publicly perform, sublicense, and distribute the 71 | Work and such Derivative Works in Source or Object form. 72 | 73 | 3. Grant of Patent License. Subject to the terms and conditions of 74 | this License, each Contributor hereby grants to You a perpetual, 75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 76 | (except as stated in this section) patent license to make, have made, 77 | use, offer to sell, sell, import, and otherwise transfer the Work, 78 | where such license applies only to those patent claims licensable 79 | by such Contributor that are necessarily infringed by their 80 | Contribution(s) alone or by combination of their Contribution(s) 81 | with the Work to which such Contribution(s) was submitted. If You 82 | institute patent litigation against any entity (including a 83 | cross-claim or counterclaim in a lawsuit) alleging that the Work 84 | or a Contribution incorporated within the Work constitutes direct 85 | or contributory patent infringement, then any patent licenses 86 | granted to You under this License for that Work shall terminate 87 | as of the date such litigation is filed. 88 | 89 | 4. Redistribution. You may reproduce and distribute copies of the 90 | Work or Derivative Works thereof in any medium, with or without 91 | modifications, and in Source or Object form, provided that You 92 | meet the following conditions: 93 | 94 | (a) You must give any other recipients of the Work or 95 | Derivative Works a copy of this License; and 96 | 97 | (b) You must cause any modified files to carry prominent notices 98 | stating that You changed the files; and 99 | 100 | (c) You must retain, in the Source form of any Derivative Works 101 | that You distribute, all copyright, patent, trademark, and 102 | attribution notices from the Source form of the Work, 103 | excluding those notices that do not pertain to any part of 104 | the Derivative Works; and 105 | 106 | (d) If the Work includes a "NOTICE" text file as part of its 107 | distribution, then any Derivative Works that You distribute must 108 | include a readable copy of the attribution notices contained 109 | within such NOTICE file, excluding those notices that do not 110 | pertain to any part of the Derivative Works, in at least one 111 | of the following places: within a NOTICE text file distributed 112 | as part of the Derivative Works; within the Source form or 113 | documentation, if provided along with the Derivative Works; or, 114 | within a display generated by the Derivative Works, if and 115 | wherever such third-party notices normally appear. The contents 116 | of the NOTICE file are for informational purposes only and 117 | do not modify the License. You may add Your own attribution 118 | notices within Derivative Works that You distribute, alongside 119 | or as an addendum to the NOTICE text from the Work, provided 120 | that such additional attribution notices cannot be construed 121 | as modifying the License. 122 | 123 | You may add Your own copyright statement to Your modifications and 124 | may provide additional or different license terms and conditions 125 | for use, reproduction, or distribution of Your modifications, or 126 | for any such Derivative Works as a whole, provided Your use, 127 | reproduction, and distribution of the Work otherwise complies with 128 | the conditions stated in this License. 129 | 130 | 5. Submission of Contributions. Unless You explicitly state otherwise, 131 | any Contribution intentionally submitted for inclusion in the Work 132 | by You to the Licensor shall be under the terms and conditions of 133 | this License, without any additional terms or conditions. 134 | Notwithstanding the above, nothing herein shall supersede or modify 135 | the terms of any separate license agreement you may have executed 136 | with Licensor regarding such Contributions. 137 | 138 | 6. Trademarks. This License does not grant permission to use the trade 139 | names, trademarks, service marks, or product names of the Licensor, 140 | except as required for reasonable and customary use in describing the 141 | origin of the Work and reproducing the content of the NOTICE file. 142 | 143 | 7. Disclaimer of Warranty. Unless required by applicable law or 144 | agreed to in writing, Licensor provides the Work (and each 145 | Contributor provides its Contributions) on an "AS IS" BASIS, 146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 147 | implied, including, without limitation, any warranties or conditions 148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 149 | PARTICULAR PURPOSE. You are solely responsible for determining the 150 | appropriateness of using or redistributing the Work and assume any 151 | risks associated with Your exercise of permissions under this License. 152 | 153 | 8. Limitation of Liability. In no event and under no legal theory, 154 | whether in tort (including negligence), contract, or otherwise, 155 | unless required by applicable law (such as deliberate and grossly 156 | negligent acts) or agreed to in writing, shall any Contributor be 157 | liable to You for damages, including any direct, indirect, special, 158 | incidental, or consequential damages of any character arising as a 159 | result of this License or out of the use or inability to use the 160 | Work (including but not limited to damages for loss of goodwill, 161 | work stoppage, computer failure or malfunction, or any and all 162 | other commercial damages or losses), even if such Contributor 163 | has been advised of the possibility of such damages. 164 | 165 | 9. Accepting Warranty or Additional Liability. While redistributing 166 | the Work or Derivative Works thereof, You may choose to offer, 167 | and charge a fee for, acceptance of support, warranty, indemnity, 168 | or other liability obligations and/or rights consistent with this 169 | License. However, in accepting such obligations, You may act only 170 | on Your own behalf and on Your sole responsibility, not on behalf 171 | of any other Contributor, and only if You agree to indemnify, 172 | defend, and hold each Contributor harmless for any liability 173 | incurred by, or claims asserted against, such Contributor by reason 174 | of your accepting any such warranty or additional liability. 175 | 176 | END OF TERMS AND CONDITIONS 177 | 178 | APPENDIX: How to apply the Apache License to your work. 179 | 180 | To apply the Apache License to your work, attach the following 181 | boilerplate notice, with the fields enclosed by brackets "[]" 182 | replaced with your own identifying information. (Don't include 183 | the brackets!) The text should be enclosed in the appropriate 184 | comment syntax for the file format. We also recommend that a 185 | file or class name and description of purpose be included on the 186 | same "printed page" as the copyright notice for easier 187 | identification within third-party archives. 188 | 189 | Copyright [yyyy] [name of copyright owner] 190 | 191 | Licensed under the Apache License, Version 2.0 (the "License"); 192 | you may not use this file except in compliance with the License. 193 | You may obtain a copy of the License at 194 | 195 | http://www.apache.org/licenses/LICENSE-2.0 196 | 197 | Unless required by applicable law or agreed to in writing, software 198 | distributed under the License is distributed on an "AS IS" BASIS, 199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 200 | See the License for the specific language governing permissions and 201 | limitations under the License. 202 | --------------------------------------------------------------------------------