Textract-py3

README.md

@@ -0,0 +1,17 @@
+# Textract-py3
+
+This is a minimally maintained fork of [deanmalmgren/textract](https://github.com/deanmalmgren/textract) to replace '*' dependencies because they block usage of `asdf`, `uvx` and modern `pip` (open issue: https://github.com/deanmalmgren/textract/issues/461).
+
+## Usage
+
+Install with `asdf plugin add textract-py3 https://github.com/amrox/asdf-pyapp.git` and `asdf install textract-py3 latest` or with `uvx` (`uv tool install textract-py3`), `mise`, etc.
+
+## Development
+
+This fork has been migrated to `poetry` and does not have CI/CD. For local testing and release, use:
+
+```sh
+poetry install --sync
+poetry run bumpversion minor
+poetry publish --build
+```

README.rst

@@ -44,4 +44,4 @@ Originally written by @deanmalmgren. Maintained by the good people at
     :target: https://github.com/deanmalmgren/textract/stargazers
 
 .. |Forks| image:: https://img.shields.io/github/forks/deanmalmgren/textract.svg
-    :target: https://github.com/deanmalmgren/textract/network
+    :target: https://github.com/deanmalmgren/textract/network

docs/changelog.rst

@@ -10,6 +10,22 @@ latest changes in development for next release
 ----------------------------------------------
 
 .. THANKS FOR CONTRIBUTING; ADD YOUR UNRELEASED CHANGES HERE!
+
+2.1.0
+-------------------
+
+* Merge minor bugfixes from upstream PRs and update documentation
+
+2.0.1
+-------------------
+
+* Fix package version and changelog
+
+2.0.0
+-------------------
+
+* Switch to poetry and relax all dependency constraints
+
 1.6.5
 -------------------
 

docs/conf.py

@@ -58,7 +58,7 @@
 # built documents.
 #
 # The short X.Y version.
-release = version = "1.6.5"
+release = version = "2.1.0"
 
 # The language for content autogenerated by Sphinx. Refer to documentation
 # for a list of supported languages.

docs/installation.rst

@@ -80,10 +80,10 @@ Don't see your operating system installation instructions here?
 
 My apologies! Installing system packages is a bit of a drag and its
 hard to anticipate all of the different environments that need to be
-accomodated (wouldn't it be awesome if there were a system-agnostic
+accommodated (wouldn't it be awesome if there were a system-agnostic
 package manager or, better yet, if python could install these system
 dependencies for you?!?!). If you're operating system doesn't have
-documenation about how to install the textract dependencies, please
+documentation about how to install the textract dependencies, please
 :ref:`contribute a pull request <contributing>` with:
 
 1. A new section in here with the appropriate details about how to

pyproject.toml

@@ -0,0 +1,38 @@
+[build-system]
+build-backend = "poetry.core.masonry.api"
+requires = ["poetry-core"]
+
+[tool.poetry]
+authors = ["Dean Malmgren <[email protected]>"]
+description = "Minimally maintained fork of deanmalmgren/textract to replace '*' dependencies "
+license = "MIT"
+name = "textract-py3"
+packages = [{include = "textract"}]
+readme = "README.md"
+repository = "https://github.com/KyleKing/textract-py3"
+version = "2.1.0"
+
+[tool.poetry.dependencies]
+python = "^3.7"
+SpeechRecognition = ">=3.8.1"
+argcomplete = ">=1.10.0"
+beautifulsoup4 = ">=4.8.0"
+chardet = ">=3"
+docx2txt = ">=0.8"
+extract-msg = ">=0.30.11"
+"pdfminer.six" = ">=20221105"
+python-pptx = ">=0.6.18"
+six = ">=1.16.0"
+xlrd = ">=1.2.0"
+pocketsphinx = {version = ">=0.1.15", optional = true}
+
+[tool.poetry.extras]
+pocketsphinx = ["pocketsphinx"]
+
+[tool.poetry.group.dev.dependencies]
+bumpversion = ">=0.6.0"
+nose = ">=1.3.7"
+pytest = ">=7.2.1"
+
+[tool.poetry.scripts]
+textract = "textract.bin.textract:main"

setup.cfg

@@ -1,8 +1,12 @@
 [bumpversion]
-current_version = 1.6.5
+current_version = 2.1.0
 commit = True
 tag = True
 
+[bumpversion:file:pyproject.toml]
+search = version = "{current_version}"
+replace = version = "{new_version}"
+
 [bumpversion:file:setup.py]
 search = version="{current_version}"
 replace = version="{new_version}"

setup.py

@@ -1,3 +1,5 @@
+# FYI: This file is kept for reference, but not used
+
 import glob
 import os
 from setuptools import setup
@@ -42,7 +44,7 @@ def parse_requirements(requirements_filename):
 
 setup(
     name=textract.__name__,
-    version="1.6.5",
+    version="2.1.0",
     description="extract text from any document. no muss. no fuss.",
     long_description=long_description,
     url=github_url,

textract/__init__.py

@@ -1,3 +1,3 @@
 from .parsers import process
 
-VERSION = "1.6.5"
+VERSION = "2.1.0"

bin/textract → textract/bin/textract.py

@@ -1,17 +1,13 @@
-#!/usr/bin/env python
-# -*- mode: python -*-
-# PYTHON_ARGCOMPLETE_OK
-
 """
 Command-line application.
 """
 
 import sys
 
-from textract.cli import get_parser
-from textract import process
-from textract.exceptions import CommandLineError
-from textract.colors import red
+from ..cli import get_parser
+from .. import process
+from ..exceptions import CommandLineError
+from ..colors import red
 
 
 # extract text
@@ -29,5 +25,3 @@ def main():
     else:
         args.output.write(output)
 
-
-main()

textract/exceptions.py

@@ -3,7 +3,7 @@
 
 # traceback from exceptions that inherit from this class are suppressed
 class CommandLineError(Exception):
-    """The traceback of all CommandLineError's is supressed when the
+    """The traceback of all CommandLineError's is suppressed when the
     errors occur on the command line to provide a useful command line
     interface.
     """

textract/parsers/msg_parser.py

@@ -8,13 +8,15 @@
 def ensure_bytes(string):
     """Normalize string to bytes.
 
-    `ExtractMsg.Message._getStringStream` can return unicode or bytes depending
+    `extract_msg.Message._getStringStream` can return unicode or bytes depending
     on what is originally stored in message file.
 
     This helper functon makes sure, that bytes type is returned.
     """
     if isinstance(string, six.string_types):
         return string.encode('utf-8')
+    if string is None:
+        return b''
     return string
 
 

textract/parsers/pdf_parser.py

@@ -8,7 +8,10 @@
 from .utils import ShellParser
 from .image import Parser as TesseractParser
 
-from distutils.spawn import find_executable
+try:
+    from shutil import which
+except ImportError:
+    from distutils.spawn import find_executable as which
 
 class Parser(ShellParser):
     """Extract text from pdf files using either the ``pdftotext`` method
@@ -49,10 +52,10 @@ def extract_pdfminer(self, filename, **kwargs):
         #Nested try/except loops? Not great
         #Try the normal pdf2txt, if that fails try the python3
         # pdf2txt, if that fails try the python2 pdf2txt
-        pdf2txt_path = find_executable('pdf2txt.py')
+        pdf2txt_path = which("pdf2txt.py")
         try:
             stdout, _ = self.run(['pdf2txt.py', filename])
-        except OSError:
+        except (OSError, ShellError):
             try:
                 stdout, _ = self.run(['python3',pdf2txt_path, filename])
             except ShellError:

textract/parsers/txt_parser.py

@@ -5,5 +5,5 @@ class Parser(BaseParser):
     """Parse ``.txt`` files"""
 
     def extract(self, filename, **kwargs):
-        with open(filename) as stream:
+        with open(filename, "rb") as stream:
             return stream.read()