text2rel 0.1__tar.gz

text2rel-0.1/PKG-INFO

@@ -0,0 +1,42 @@
+Metadata-Version: 2.3
+Name: text2rel
+Version: 0.1
+Summary: An HTML cleaner customized for kinship ties extraction from large text corpra.
+Requires-Python: >=3.10,<3.13
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Requires-Dist: beautifulsoup4 (>=4.12,<5.0)
+Requires-Dist: numpy (==1.26.4)
+Requires-Dist: pandas (==2.2.2)
+Requires-Dist: regex
+Description-Content-Type: text/markdown
+
+![Alt text](images/Kinship_Ties_Extraction.png)
+![PyPI version](https://img.shields.io/pypi/v/html-cleaner-kinship)
+
+
+
+This is the package implementation of the code for the kinship ties and relational information from large text corpora, such as genealogies, biographies, and historical dictionaries. 
+
+### Important information: 
+- For example package usage, see ```test_workflow.ipynb```
+- For information about individual functions before the package implementation and release, see ```examples``` folder. 
+
+### Current release: 
+Current release includes inventory creation, setting text bounds, assigning font usage and selecting appropriate text chunks from the files (including restriction to "MainText" fonts and JumPJumP insertion). 
+
+### Files structure: 
+
+1. #### cleaner.py 
+Contains the HTMLCleaner class and thus the main logic. 
+
+2. #### utils.py
+Contains helper functions (like JumPJumP insertion)
+
+3. #### io.py
+Contains the file processing logic, such as loading and saving the JSON inventory. 
+
+
+

text2rel-0.1/pyproject.toml

@@ -0,0 +1,18 @@
+[tool.poetry]
+name = "text2rel"
+version = "0.1"
+description = "An HTML cleaner customized for kinship ties extraction from large text corpra."
+
+readme = "readme.md"
+
+[tool.poetry.dependencies]
+python = ">=3.10,<3.13"
+pandas = "2.2.2"
+numpy = "1.26.4"
+regex = "*"
+beautifulsoup4 = "^4.12"
+
+
+[build-system]
+build-backend = "poetry.core.masonry.api"
+requires = ["poetry-core>=1.0.0"]

text2rel-0.1/readme.md

@@ -0,0 +1,26 @@
+![Alt text](images/Kinship_Ties_Extraction.png)
+![PyPI version](https://img.shields.io/pypi/v/html-cleaner-kinship)
+
+
+
+This is the package implementation of the code for the kinship ties and relational information from large text corpora, such as genealogies, biographies, and historical dictionaries. 
+
+### Important information: 
+- For example package usage, see ```test_workflow.ipynb```
+- For information about individual functions before the package implementation and release, see ```examples``` folder. 
+
+### Current release: 
+Current release includes inventory creation, setting text bounds, assigning font usage and selecting appropriate text chunks from the files (including restriction to "MainText" fonts and JumPJumP insertion). 
+
+### Files structure: 
+
+1. #### cleaner.py 
+Contains the HTMLCleaner class and thus the main logic. 
+
+2. #### utils.py
+Contains helper functions (like JumPJumP insertion)
+
+3. #### io.py
+Contains the file processing logic, such as loading and saving the JSON inventory. 
+
+

text2rel-0.1/text2rel/__init__.py

@@ -0,0 +1,3 @@
+from .cleaner import HTMLCleaner
+from .llm_processor import LLMProcessor
+__all__ = ["HTMLCleaner", "LLMProcessor"]