pyxtxt 0.3.6__tar.gz → 0.3.7__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- {pyxtxt-0.3.6/src/pyxtxt.egg-info → pyxtxt-0.3.7}/PKG-INFO +10 -6
- {pyxtxt-0.3.6 → pyxtxt-0.3.7}/README.md +7 -1
- {pyxtxt-0.3.6 → pyxtxt-0.3.7}/pyproject.toml +3 -5
- {pyxtxt-0.3.6 → pyxtxt-0.3.7/src/pyxtxt.egg-info}/PKG-INFO +10 -6
- {pyxtxt-0.3.6 → pyxtxt-0.3.7}/LICENSE +0 -0
- {pyxtxt-0.3.6 → pyxtxt-0.3.7}/setup.cfg +0 -0
- {pyxtxt-0.3.6 → pyxtxt-0.3.7}/src/pyxtxt/__init__.py +0 -0
- {pyxtxt-0.3.6 → pyxtxt-0.3.7}/src/pyxtxt/core.py +0 -0
- {pyxtxt-0.3.6 → pyxtxt-0.3.7}/src/pyxtxt/estrattori/__init__.py +0 -0
- {pyxtxt-0.3.6 → pyxtxt-0.3.7}/src/pyxtxt/estrattori/audio.py +0 -0
- {pyxtxt-0.3.6 → pyxtxt-0.3.7}/src/pyxtxt/estrattori/doc.py +0 -0
- {pyxtxt-0.3.6 → pyxtxt-0.3.7}/src/pyxtxt/estrattori/docx.py +0 -0
- {pyxtxt-0.3.6 → pyxtxt-0.3.7}/src/pyxtxt/estrattori/eml.py +0 -0
- {pyxtxt-0.3.6 → pyxtxt-0.3.7}/src/pyxtxt/estrattori/epub.py +0 -0
- {pyxtxt-0.3.6 → pyxtxt-0.3.7}/src/pyxtxt/estrattori/exif.py +0 -0
- {pyxtxt-0.3.6 → pyxtxt-0.3.7}/src/pyxtxt/estrattori/html.py +0 -0
- {pyxtxt-0.3.6 → pyxtxt-0.3.7}/src/pyxtxt/estrattori/md.py +0 -0
- {pyxtxt-0.3.6 → pyxtxt-0.3.7}/src/pyxtxt/estrattori/msg.py +0 -0
- {pyxtxt-0.3.6 → pyxtxt-0.3.7}/src/pyxtxt/estrattori/ocr.py +0 -0
- {pyxtxt-0.3.6 → pyxtxt-0.3.7}/src/pyxtxt/estrattori/ocr_ollama.py +0 -0
- {pyxtxt-0.3.6 → pyxtxt-0.3.7}/src/pyxtxt/estrattori/odt.py +0 -0
- {pyxtxt-0.3.6 → pyxtxt-0.3.7}/src/pyxtxt/estrattori/pdf.py +0 -0
- {pyxtxt-0.3.6 → pyxtxt-0.3.7}/src/pyxtxt/estrattori/pptx.py +0 -0
- {pyxtxt-0.3.6 → pyxtxt-0.3.7}/src/pyxtxt/estrattori/rtf.py +0 -0
- {pyxtxt-0.3.6 → pyxtxt-0.3.7}/src/pyxtxt/estrattori/svg.py +0 -0
- {pyxtxt-0.3.6 → pyxtxt-0.3.7}/src/pyxtxt/estrattori/tex.py +0 -0
- {pyxtxt-0.3.6 → pyxtxt-0.3.7}/src/pyxtxt/estrattori/txt.py +0 -0
- {pyxtxt-0.3.6 → pyxtxt-0.3.7}/src/pyxtxt/estrattori/xls.py +0 -0
- {pyxtxt-0.3.6 → pyxtxt-0.3.7}/src/pyxtxt/estrattori/xlsx.py +0 -0
- {pyxtxt-0.3.6 → pyxtxt-0.3.7}/src/pyxtxt/estrattori/xml.py +0 -0
- {pyxtxt-0.3.6 → pyxtxt-0.3.7}/src/pyxtxt/examples.py +0 -0
- {pyxtxt-0.3.6 → pyxtxt-0.3.7}/src/pyxtxt.egg-info/SOURCES.txt +0 -0
- {pyxtxt-0.3.6 → pyxtxt-0.3.7}/src/pyxtxt.egg-info/dependency_links.txt +0 -0
- {pyxtxt-0.3.6 → pyxtxt-0.3.7}/src/pyxtxt.egg-info/requires.txt +0 -0
- {pyxtxt-0.3.6 → pyxtxt-0.3.7}/src/pyxtxt.egg-info/top_level.txt +0 -0
- {pyxtxt-0.3.6 → pyxtxt-0.3.7}/tests/test_extraction.py +0 -0
- {pyxtxt-0.3.6 → pyxtxt-0.3.7}/tests/test_import.py +0 -0
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.4
|
|
2
2
|
Name: pyxtxt
|
|
3
|
-
Version: 0.3.
|
|
3
|
+
Version: 0.3.7
|
|
4
4
|
Summary: A Python library for extracting text from different types of files (PDF, DOCX, PPTX, XLSX, ODT, etc.).
|
|
5
5
|
Author-email: Giuseppe Levi <giuseppe.levi@gmail.com>
|
|
6
6
|
License-Expression: MIT
|
|
@@ -11,16 +11,14 @@ Classifier: Development Status :: 4 - Beta
|
|
|
11
11
|
Classifier: Intended Audience :: Developers
|
|
12
12
|
Classifier: Operating System :: OS Independent
|
|
13
13
|
Classifier: Programming Language :: Python :: 3
|
|
14
|
-
Classifier: Programming Language :: Python :: 3.7
|
|
15
|
-
Classifier: Programming Language :: Python :: 3.8
|
|
16
|
-
Classifier: Programming Language :: Python :: 3.9
|
|
17
14
|
Classifier: Programming Language :: Python :: 3.10
|
|
18
15
|
Classifier: Programming Language :: Python :: 3.11
|
|
19
16
|
Classifier: Programming Language :: Python :: 3.12
|
|
20
17
|
Classifier: Programming Language :: Python :: 3.13
|
|
18
|
+
Classifier: Programming Language :: Python :: 3.14
|
|
21
19
|
Classifier: Topic :: Text Processing
|
|
22
20
|
Classifier: Topic :: Utilities
|
|
23
|
-
Requires-Python: >=3.
|
|
21
|
+
Requires-Python: >=3.10
|
|
24
22
|
Description-Content-Type: text/markdown
|
|
25
23
|
License-File: LICENSE
|
|
26
24
|
Requires-Dist: python-magic; sys_platform != "win32"
|
|
@@ -149,6 +147,8 @@ print(extxt_available_formats(pretty=True)) # Short names
|
|
|
149
147
|
|
|
150
148
|
## 📦 Installation
|
|
151
149
|
|
|
150
|
+
PyxTxt requires Python 3.10 or newer.
|
|
151
|
+
|
|
152
152
|
Install every extractor (this includes the heavy audio and OCR dependencies):
|
|
153
153
|
|
|
154
154
|
```bash
|
|
@@ -374,7 +374,7 @@ pip install -e ".[pdf,docx,presentation,spreadsheet,odf,html,markdown,epub,rtf,e
|
|
|
374
374
|
pytest
|
|
375
375
|
```
|
|
376
376
|
|
|
377
|
-
Tests for formats whose libraries are not installed are skipped. CI runs the test suite on Python 3.10–3.
|
|
377
|
+
Tests for formats whose libraries are not installed are skipped. CI runs the test suite on Python 3.10–3.14.
|
|
378
378
|
|
|
379
379
|
### Releasing
|
|
380
380
|
|
|
@@ -407,6 +407,10 @@ Pull requests, issues and feedback are welcome.
|
|
|
407
407
|
|
|
408
408
|
## 📊 Changelog
|
|
409
409
|
|
|
410
|
+
### v0.3.7
|
|
411
|
+
- Python 3.10 or newer is now required; metadata no longer lists the end-of-life versions 3.7–3.9, which were never tested
|
|
412
|
+
- Python 3.14 is tested in CI and declared as supported
|
|
413
|
+
|
|
410
414
|
### v0.3.6
|
|
411
415
|
- **FIXED**: `import pyxtxt` crashed with `AttributeError` unless both `ollama` and Pillow were installed (regression in 0.3.4.2 and 0.3.5)
|
|
412
416
|
- **FIXED**: Markdown, RTF and LaTeX files were returned as raw source instead of being converted to text
|
|
@@ -64,6 +64,8 @@ print(extxt_available_formats(pretty=True)) # Short names
|
|
|
64
64
|
|
|
65
65
|
## 📦 Installation
|
|
66
66
|
|
|
67
|
+
PyxTxt requires Python 3.10 or newer.
|
|
68
|
+
|
|
67
69
|
Install every extractor (this includes the heavy audio and OCR dependencies):
|
|
68
70
|
|
|
69
71
|
```bash
|
|
@@ -289,7 +291,7 @@ pip install -e ".[pdf,docx,presentation,spreadsheet,odf,html,markdown,epub,rtf,e
|
|
|
289
291
|
pytest
|
|
290
292
|
```
|
|
291
293
|
|
|
292
|
-
Tests for formats whose libraries are not installed are skipped. CI runs the test suite on Python 3.10–3.
|
|
294
|
+
Tests for formats whose libraries are not installed are skipped. CI runs the test suite on Python 3.10–3.14.
|
|
293
295
|
|
|
294
296
|
### Releasing
|
|
295
297
|
|
|
@@ -322,6 +324,10 @@ Pull requests, issues and feedback are welcome.
|
|
|
322
324
|
|
|
323
325
|
## 📊 Changelog
|
|
324
326
|
|
|
327
|
+
### v0.3.7
|
|
328
|
+
- Python 3.10 or newer is now required; metadata no longer lists the end-of-life versions 3.7–3.9, which were never tested
|
|
329
|
+
- Python 3.14 is tested in CI and declared as supported
|
|
330
|
+
|
|
325
331
|
### v0.3.6
|
|
326
332
|
- **FIXED**: `import pyxtxt` crashed with `AttributeError` unless both `ollama` and Pillow were installed (regression in 0.3.4.2 and 0.3.5)
|
|
327
333
|
- **FIXED**: Markdown, RTF and LaTeX files were returned as raw source instead of being converted to text
|
|
@@ -1,25 +1,23 @@
|
|
|
1
1
|
[project]
|
|
2
2
|
name = "pyxtxt"
|
|
3
|
-
version = "0.3.
|
|
3
|
+
version = "0.3.7"
|
|
4
4
|
description = "A Python library for extracting text from different types of files (PDF, DOCX, PPTX, XLSX, ODT, etc.)."
|
|
5
5
|
classifiers = [
|
|
6
6
|
"Development Status :: 4 - Beta",
|
|
7
7
|
"Intended Audience :: Developers",
|
|
8
8
|
"Operating System :: OS Independent",
|
|
9
9
|
"Programming Language :: Python :: 3",
|
|
10
|
-
"Programming Language :: Python :: 3.7",
|
|
11
|
-
"Programming Language :: Python :: 3.8",
|
|
12
|
-
"Programming Language :: Python :: 3.9",
|
|
13
10
|
"Programming Language :: Python :: 3.10",
|
|
14
11
|
"Programming Language :: Python :: 3.11",
|
|
15
12
|
"Programming Language :: Python :: 3.12",
|
|
16
13
|
"Programming Language :: Python :: 3.13",
|
|
14
|
+
"Programming Language :: Python :: 3.14",
|
|
17
15
|
"Topic :: Text Processing",
|
|
18
16
|
"Topic :: Utilities"
|
|
19
17
|
]
|
|
20
18
|
|
|
21
19
|
readme = "README.md"
|
|
22
|
-
requires-python = ">=3.
|
|
20
|
+
requires-python = ">=3.10"
|
|
23
21
|
|
|
24
22
|
license = "MIT"
|
|
25
23
|
license-files = ["LICENSE"]
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.4
|
|
2
2
|
Name: pyxtxt
|
|
3
|
-
Version: 0.3.
|
|
3
|
+
Version: 0.3.7
|
|
4
4
|
Summary: A Python library for extracting text from different types of files (PDF, DOCX, PPTX, XLSX, ODT, etc.).
|
|
5
5
|
Author-email: Giuseppe Levi <giuseppe.levi@gmail.com>
|
|
6
6
|
License-Expression: MIT
|
|
@@ -11,16 +11,14 @@ Classifier: Development Status :: 4 - Beta
|
|
|
11
11
|
Classifier: Intended Audience :: Developers
|
|
12
12
|
Classifier: Operating System :: OS Independent
|
|
13
13
|
Classifier: Programming Language :: Python :: 3
|
|
14
|
-
Classifier: Programming Language :: Python :: 3.7
|
|
15
|
-
Classifier: Programming Language :: Python :: 3.8
|
|
16
|
-
Classifier: Programming Language :: Python :: 3.9
|
|
17
14
|
Classifier: Programming Language :: Python :: 3.10
|
|
18
15
|
Classifier: Programming Language :: Python :: 3.11
|
|
19
16
|
Classifier: Programming Language :: Python :: 3.12
|
|
20
17
|
Classifier: Programming Language :: Python :: 3.13
|
|
18
|
+
Classifier: Programming Language :: Python :: 3.14
|
|
21
19
|
Classifier: Topic :: Text Processing
|
|
22
20
|
Classifier: Topic :: Utilities
|
|
23
|
-
Requires-Python: >=3.
|
|
21
|
+
Requires-Python: >=3.10
|
|
24
22
|
Description-Content-Type: text/markdown
|
|
25
23
|
License-File: LICENSE
|
|
26
24
|
Requires-Dist: python-magic; sys_platform != "win32"
|
|
@@ -149,6 +147,8 @@ print(extxt_available_formats(pretty=True)) # Short names
|
|
|
149
147
|
|
|
150
148
|
## 📦 Installation
|
|
151
149
|
|
|
150
|
+
PyxTxt requires Python 3.10 or newer.
|
|
151
|
+
|
|
152
152
|
Install every extractor (this includes the heavy audio and OCR dependencies):
|
|
153
153
|
|
|
154
154
|
```bash
|
|
@@ -374,7 +374,7 @@ pip install -e ".[pdf,docx,presentation,spreadsheet,odf,html,markdown,epub,rtf,e
|
|
|
374
374
|
pytest
|
|
375
375
|
```
|
|
376
376
|
|
|
377
|
-
Tests for formats whose libraries are not installed are skipped. CI runs the test suite on Python 3.10–3.
|
|
377
|
+
Tests for formats whose libraries are not installed are skipped. CI runs the test suite on Python 3.10–3.14.
|
|
378
378
|
|
|
379
379
|
### Releasing
|
|
380
380
|
|
|
@@ -407,6 +407,10 @@ Pull requests, issues and feedback are welcome.
|
|
|
407
407
|
|
|
408
408
|
## 📊 Changelog
|
|
409
409
|
|
|
410
|
+
### v0.3.7
|
|
411
|
+
- Python 3.10 or newer is now required; metadata no longer lists the end-of-life versions 3.7–3.9, which were never tested
|
|
412
|
+
- Python 3.14 is tested in CI and declared as supported
|
|
413
|
+
|
|
410
414
|
### v0.3.6
|
|
411
415
|
- **FIXED**: `import pyxtxt` crashed with `AttributeError` unless both `ollama` and Pillow were installed (regression in 0.3.4.2 and 0.3.5)
|
|
412
416
|
- **FIXED**: Markdown, RTF and LaTeX files were returned as raw source instead of being converted to text
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|