polytext 0.2.8b2__tar.gz → 0.2.8b3__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.
Files changed (99) hide show
  1. {polytext-0.2.8b2 → polytext-0.2.8b3}/PKG-INFO +1 -1
  2. {polytext-0.2.8b2 → polytext-0.2.8b3}/polytext/converter/audio_to_text.py +9 -4
  3. {polytext-0.2.8b2 → polytext-0.2.8b3}/polytext.egg-info/PKG-INFO +1 -1
  4. {polytext-0.2.8b2 → polytext-0.2.8b3}/setup.py +1 -1
  5. {polytext-0.2.8b2 → polytext-0.2.8b3}/LICENSE +0 -0
  6. {polytext-0.2.8b2 → polytext-0.2.8b3}/README.md +0 -0
  7. {polytext-0.2.8b2 → polytext-0.2.8b3}/polytext/__init__.py +0 -0
  8. {polytext-0.2.8b2 → polytext-0.2.8b3}/polytext/converter/__init__.py +0 -0
  9. {polytext-0.2.8b2 → polytext-0.2.8b3}/polytext/converter/base.py +0 -0
  10. {polytext-0.2.8b2 → polytext-0.2.8b3}/polytext/converter/beautiful_text.py +0 -0
  11. {polytext-0.2.8b2 → polytext-0.2.8b3}/polytext/converter/document_ocr_to_text.py +0 -0
  12. {polytext-0.2.8b2 → polytext-0.2.8b3}/polytext/converter/document_ocr_to_text_azure_oai.py +0 -0
  13. {polytext-0.2.8b2 → polytext-0.2.8b3}/polytext/converter/gemini_quality_guards.py +0 -0
  14. {polytext-0.2.8b2 → polytext-0.2.8b3}/polytext/converter/html_to_md.py +0 -0
  15. {polytext-0.2.8b2 → polytext-0.2.8b3}/polytext/converter/md_to_text.py +0 -0
  16. {polytext-0.2.8b2 → polytext-0.2.8b3}/polytext/converter/ocr_to_text.py +0 -0
  17. {polytext-0.2.8b2 → polytext-0.2.8b3}/polytext/converter/ocr_to_text_azure_oai.py +0 -0
  18. {polytext-0.2.8b2 → polytext-0.2.8b3}/polytext/converter/pdf.py +0 -0
  19. {polytext-0.2.8b2 → polytext-0.2.8b3}/polytext/converter/text_to_md.py +0 -0
  20. {polytext-0.2.8b2 → polytext-0.2.8b3}/polytext/converter/video_to_audio.py +0 -0
  21. {polytext-0.2.8b2 → polytext-0.2.8b3}/polytext/exceptions/__init__.py +0 -0
  22. {polytext-0.2.8b2 → polytext-0.2.8b3}/polytext/exceptions/base.py +0 -0
  23. {polytext-0.2.8b2 → polytext-0.2.8b3}/polytext/generator/__init__.py +0 -0
  24. {polytext-0.2.8b2 → polytext-0.2.8b3}/polytext/generator/pdf.py +0 -0
  25. {polytext-0.2.8b2 → polytext-0.2.8b3}/polytext/loader/__init__.py +0 -0
  26. {polytext-0.2.8b2 → polytext-0.2.8b3}/polytext/loader/audio.py +0 -0
  27. {polytext-0.2.8b2 → polytext-0.2.8b3}/polytext/loader/aws_auth.py +0 -0
  28. {polytext-0.2.8b2 → polytext-0.2.8b3}/polytext/loader/base.py +0 -0
  29. {polytext-0.2.8b2 → polytext-0.2.8b3}/polytext/loader/document.py +0 -0
  30. {polytext-0.2.8b2 → polytext-0.2.8b3}/polytext/loader/document_ocr.py +0 -0
  31. {polytext-0.2.8b2 → polytext-0.2.8b3}/polytext/loader/downloader/__init__.py +0 -0
  32. {polytext-0.2.8b2 → polytext-0.2.8b3}/polytext/loader/downloader/downloader.py +0 -0
  33. {polytext-0.2.8b2 → polytext-0.2.8b3}/polytext/loader/html.py +0 -0
  34. {polytext-0.2.8b2 → polytext-0.2.8b3}/polytext/loader/markdown.py +0 -0
  35. {polytext-0.2.8b2 → polytext-0.2.8b3}/polytext/loader/notebook.py +0 -0
  36. {polytext-0.2.8b2 → polytext-0.2.8b3}/polytext/loader/ocr.py +0 -0
  37. {polytext-0.2.8b2 → polytext-0.2.8b3}/polytext/loader/plain_text.py +0 -0
  38. {polytext-0.2.8b2 → polytext-0.2.8b3}/polytext/loader/video.py +0 -0
  39. {polytext-0.2.8b2 → polytext-0.2.8b3}/polytext/loader/xml_xbrl.py +0 -0
  40. {polytext-0.2.8b2 → polytext-0.2.8b3}/polytext/loader/youtube.py +0 -0
  41. {polytext-0.2.8b2 → polytext-0.2.8b3}/polytext/loader/youtube_llm.py +0 -0
  42. {polytext-0.2.8b2 → polytext-0.2.8b3}/polytext/processor/__init__.py +0 -0
  43. {polytext-0.2.8b2 → polytext-0.2.8b3}/polytext/processor/audio_chunker.py +0 -0
  44. {polytext-0.2.8b2 → polytext-0.2.8b3}/polytext/processor/text_merger.py +0 -0
  45. {polytext-0.2.8b2 → polytext-0.2.8b3}/polytext/processor/transcript_chunker.py +0 -0
  46. {polytext-0.2.8b2 → polytext-0.2.8b3}/polytext/prompts/__init__.py +0 -0
  47. {polytext-0.2.8b2 → polytext-0.2.8b3}/polytext/prompts/beautiful_text.py +0 -0
  48. {polytext-0.2.8b2 → polytext-0.2.8b3}/polytext/prompts/ocr.py +0 -0
  49. {polytext-0.2.8b2 → polytext-0.2.8b3}/polytext/prompts/text_merging.py +0 -0
  50. {polytext-0.2.8b2 → polytext-0.2.8b3}/polytext/prompts/text_to_md.py +0 -0
  51. {polytext-0.2.8b2 → polytext-0.2.8b3}/polytext/prompts/transcription.py +0 -0
  52. {polytext-0.2.8b2 → polytext-0.2.8b3}/polytext/utils/__init__.py +0 -0
  53. {polytext-0.2.8b2 → polytext-0.2.8b3}/polytext/utils/utils.py +0 -0
  54. {polytext-0.2.8b2 → polytext-0.2.8b3}/polytext.egg-info/SOURCES.txt +0 -0
  55. {polytext-0.2.8b2 → polytext-0.2.8b3}/polytext.egg-info/dependency_links.txt +0 -0
  56. {polytext-0.2.8b2 → polytext-0.2.8b3}/polytext.egg-info/not-zip-safe +0 -0
  57. {polytext-0.2.8b2 → polytext-0.2.8b3}/polytext.egg-info/requires.txt +0 -0
  58. {polytext-0.2.8b2 → polytext-0.2.8b3}/polytext.egg-info/top_level.txt +0 -0
  59. {polytext-0.2.8b2 → polytext-0.2.8b3}/pyproject.toml +0 -0
  60. {polytext-0.2.8b2 → polytext-0.2.8b3}/setup.cfg +0 -0
  61. {polytext-0.2.8b2 → polytext-0.2.8b3}/tests/test_audio_chunker.py +0 -0
  62. {polytext-0.2.8b2 → polytext-0.2.8b3}/tests/test_audio_comparison_helpers.py +0 -0
  63. {polytext-0.2.8b2 → polytext-0.2.8b3}/tests/test_audio_transcription_model_migration.py +0 -0
  64. {polytext-0.2.8b2 → polytext-0.2.8b3}/tests/test_aws_auth.py +0 -0
  65. {polytext-0.2.8b2 → polytext-0.2.8b3}/tests/test_base_loader_error_mapping.py +0 -0
  66. {polytext-0.2.8b2 → polytext-0.2.8b3}/tests/test_beautiful_text_manual.py +0 -0
  67. {polytext-0.2.8b2 → polytext-0.2.8b3}/tests/test_compare_audio_models.py +0 -0
  68. {polytext-0.2.8b2 → polytext-0.2.8b3}/tests/test_compare_document_ocr_to_text_models.py +0 -0
  69. {polytext-0.2.8b2 → polytext-0.2.8b3}/tests/test_compare_ocr_to_text_models.py +0 -0
  70. {polytext-0.2.8b2 → polytext-0.2.8b3}/tests/test_compare_youtube_models.py +0 -0
  71. {polytext-0.2.8b2 → polytext-0.2.8b3}/tests/test_dowload_audio_from_youtube.py +0 -0
  72. {polytext-0.2.8b2 → polytext-0.2.8b3}/tests/test_dowload_audio_from_youtube_helpers.py +0 -0
  73. {polytext-0.2.8b2 → polytext-0.2.8b3}/tests/test_extracted_text_whitespace.py +0 -0
  74. {polytext-0.2.8b2 → polytext-0.2.8b3}/tests/test_gemini_quality_guards.py +0 -0
  75. {polytext-0.2.8b2 → polytext-0.2.8b3}/tests/test_get_audio_transcript_from_gcs.py +0 -0
  76. {polytext-0.2.8b2 → polytext-0.2.8b3}/tests/test_get_customized_pdf_from_markdown.py +0 -0
  77. {polytext-0.2.8b2 → polytext-0.2.8b3}/tests/test_get_document_ocr.py +0 -0
  78. {polytext-0.2.8b2 → polytext-0.2.8b3}/tests/test_get_document_ocr_azure_oai.py +0 -0
  79. {polytext-0.2.8b2 → polytext-0.2.8b3}/tests/test_get_document_text.py +0 -0
  80. {polytext-0.2.8b2 → polytext-0.2.8b3}/tests/test_get_document_text_from_gcs.py +0 -0
  81. {polytext-0.2.8b2 → polytext-0.2.8b3}/tests/test_get_ocr_from_image.py +0 -0
  82. {polytext-0.2.8b2 → polytext-0.2.8b3}/tests/test_get_text_from_markdown.py +0 -0
  83. {polytext-0.2.8b2 → polytext-0.2.8b3}/tests/test_get_video_transcript_from_gcs.py +0 -0
  84. {polytext-0.2.8b2 → polytext-0.2.8b3}/tests/test_library.py +0 -0
  85. {polytext-0.2.8b2 → polytext-0.2.8b3}/tests/test_markdown_loader_gzip.py +0 -0
  86. {polytext-0.2.8b2 → polytext-0.2.8b3}/tests/test_markitdown_html.py +0 -0
  87. {polytext-0.2.8b2 → polytext-0.2.8b3}/tests/test_notebook_loader.py +0 -0
  88. {polytext-0.2.8b2 → polytext-0.2.8b3}/tests/test_ocr_fallbacks.py +0 -0
  89. {polytext-0.2.8b2 → polytext-0.2.8b3}/tests/test_ocr_image_descriptions.py +0 -0
  90. {polytext-0.2.8b2 → polytext-0.2.8b3}/tests/test_pain_text.py +0 -0
  91. {polytext-0.2.8b2 → polytext-0.2.8b3}/tests/test_pdf_conversion_error.py +0 -0
  92. {polytext-0.2.8b2 → polytext-0.2.8b3}/tests/test_python_version_metadata.py +0 -0
  93. {polytext-0.2.8b2 → polytext-0.2.8b3}/tests/test_split_audio_with_llm.py +0 -0
  94. {polytext-0.2.8b2 → polytext-0.2.8b3}/tests/test_transcribe_s3_images_from_csv.py +0 -0
  95. {polytext-0.2.8b2 → polytext-0.2.8b3}/tests/test_transcribe_s3_images_from_csv_script.py +0 -0
  96. {polytext-0.2.8b2 → polytext-0.2.8b3}/tests/test_xml_xbrl_loader.py +0 -0
  97. {polytext-0.2.8b2 → polytext-0.2.8b3}/tests/test_youtube_gemini_minimal_check.py +0 -0
  98. {polytext-0.2.8b2 → polytext-0.2.8b3}/tests/test_youtube_llm_fallbacks.py +0 -0
  99. {polytext-0.2.8b2 → polytext-0.2.8b3}/tests/test_youtube_transcript.py +0 -0
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: polytext
3
- Version: 0.2.8b2
3
+ Version: 0.2.8b3
4
4
  Summary: Python utilities to simplify document files management
5
5
  Home-page: https://github.com/docsity/polytext
6
6
  Author: Matteo Senardi
@@ -80,23 +80,30 @@ def add_line_break_after_each_sentence(text: str) -> str:
80
80
  if not text:
81
81
  return text
82
82
 
83
+ line_feed = chr(10)
83
84
  lines = text.splitlines()
84
85
  formatted_lines = []
85
86
 
86
87
  for line in lines:
87
88
  stripped_line = line.strip()
89
+
88
90
  if not stripped_line:
89
91
  formatted_lines.append("")
90
92
  continue
93
+
91
94
  if re.match(r"^#{1,6}\s+", stripped_line):
92
95
  formatted_lines.append(stripped_line)
93
96
  continue
94
97
 
95
98
  normalized_line = re.sub(r"\s+", " ", stripped_line)
96
- normalized_line = re.sub(r"([.!?])\s+", r"\1\\n ", normalized_line)
99
+ normalized_line = re.sub(
100
+ r"([.!?])\s+",
101
+ lambda match: f"{match.group(1)}{line_feed} ",
102
+ normalized_line,
103
+ )
97
104
  formatted_lines.append(normalized_line)
98
105
 
99
- return "\\n ".join(formatted_lines).strip()
106
+ return line_feed.join(formatted_lines).strip()
100
107
 
101
108
 
102
109
  def create_ascii_safe_upload_copy(audio_file: str) -> tuple[str, str | None]:
@@ -537,8 +544,6 @@ class AudioToTextConverter:
537
544
  )
538
545
 
539
546
  response_text, marker_only = normalize_no_human_speech_marker(response_text)
540
- if not marker_only:
541
- response_text = self.format_audio_output_text(response_text)
542
547
 
543
548
  response_dict = {
544
549
  "transcript": "" if marker_only else response_text,
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: polytext
3
- Version: 0.2.8b2
3
+ Version: 0.2.8b3
4
4
  Summary: Python utilities to simplify document files management
5
5
  Home-page: https://github.com/docsity/polytext
6
6
  Author: Matteo Senardi
@@ -51,7 +51,7 @@ def get_requirements(*requirements_file):
51
51
 
52
52
  setup(
53
53
  name='polytext',
54
- version='0.2.8b2',
54
+ version='0.2.8b3',
55
55
  url='https://github.com/docsity/polytext',
56
56
  # download_url='https://github.com/pualien/py-polytext/archive/0.1.23.tar.gz',
57
57
  license='MIT',
File without changes
File without changes
File without changes
File without changes