mistocr 0.2.6__py3-none-any.whl → 0.2.8__py3-none-any.whl

mistocr/__init__.py

@@ -1 +1 @@
-__version__ = "0.2.6"
+__version__ = "0.2.8"

mistocr/refine.py

@@ -3,10 +3,10 @@
 # AUTOGENERATED! DO NOT EDIT! File to edit: ../nbs/01_refine.ipynb.
 
 # %% auto 0
-__all__ = ['prompt_fix_hdgs', 'describe_img_prompt', 'get_hdgs', 'add_pg_hdgs', 'read_pgs_pg', 'fmt_hdgs_idx',
-           'HeadingCorrection', 'HeadingCorrections', 'fix_hdg_hierarchy', 'mk_fixes_lut', 'apply_hdg_fixes',
-           'fix_hdgs', 'ImgDescription', 'describe_img', 'limit', 'parse_r', 'describe_imgs', 'save_img_descs',
-           'add_descs_to_pg', 'add_descs_to_pgs', 'add_img_descs']
+__all__ = ['describe_img_prompt', 'get_hdgs', 'add_pg_hdgs', 'read_pgs_pg', 'fmt_hdgs_idx', 'HeadingCorrection',
+           'HeadingCorrections', 'fix_hdg_hierarchy', 'mk_fixes_lut', 'apply_hdg_fixes', 'fix_hdgs', 'ImgDescription',
+           'describe_img', 'limit', 'parse_r', 'describe_imgs', 'save_img_descs', 'add_descs_to_pg', 'add_descs_to_pgs',
+           'add_img_descs']
 
 # %% ../nbs/01_refine.ipynb 3
 from fastcore.all import *
@@ -66,39 +66,6 @@ class HeadingCorrection(BaseModel):
 class HeadingCorrections(BaseModel):
     corrections: list[HeadingCorrection]
 
-# %% ../nbs/01_refine.ipynb 20
-prompt_fix_hdgs = """Fix markdown heading hierarchy errors while preserving the document's intended structure.
-
-INPUT FORMAT: Each heading is prefixed with its index number (e.g., "0. # Title ... page 1")
-
-RULES - Apply these fixes in order:
-
-1. **Single H1 rule**: Documents must have exactly ONE # heading (typically the document title at the top)
-   - If index 0 is already #, then all subsequent headings (index 1+) must be ## or deeper
-   - If no H1 exists, the first major heading should be #, and all others ## or deeper
-   - NO exceptions: appendices, references, and all sections are ## or deeper after the title
-
-2. **Infer depth from numbering patterns**: If headings contain section numbers, deeper nesting means deeper heading level
-   - Parent section (e.g., "1", "2", "A") should be shallower than child (e.g., "1.1", "2.a", "A.1")
-   - Child section should be one # deeper than parent
-   - Works with any numbering: "1/1.1/1.1.1", "A/A.1/A.1.a", "I/I.A/I.A.1", etc.
-
-3. **Level jumps**: Headings can only increase by one # at a time when moving deeper
-   - Wrong: ## Section → ##### Subsection
-   - Fixed: ## Section → ### Subsection
-
-4. **Decreasing levels is OK**: Moving back up the hierarchy (### to ##) is valid for new sections
-
-OUTPUT: Return a list of corrections, where each correction has:
-- index: the heading's index number
-- corrected: the fixed heading text (without the index prefix)
-IMPORTANT: Preserve the " ... page N" suffix in all corrected headings.
-Only include headings that need changes.
-
-Headings to analyze:
-{headings_list}
-"""
-
 # %% ../nbs/01_refine.ipynb 22
 def fix_hdg_hierarchy(
     hdgs: list[str], # List of markdown headings
@@ -253,6 +220,12 @@ async def add_img_descs(
     src_path,dst_path = Path(src),Path(dst) if dst else Path(src)
     if dst_path != src_path: dst_path.mkdir(parents=True, exist_ok=True)
     src_imgs = src_path/img_folder
+    
+    # Check if image folder exists
+    if not src_imgs.exists():
+        if progress: print(f"No images to describe in the document (no '{img_folder}' folder found)")
+        return
+    
     if src_imgs.exists() and dst_path != src_path: shutil.copytree(src_imgs, dst_path/img_folder, dirs_exist_ok=True)
     desc_file = src_path/'img_descriptions.json'
     if desc_file.exists() and not force:
@@ -269,3 +242,4 @@ async def add_img_descs(
     enriched = [add_descs_to_pg(pg, descs) for pg in pgs]
     for i,pg in enumerate(enriched, 1): (dst_path/f'page_{i}.md').write_text(pg)
     if progress: print(f"Done! Enriched pages saved to {dst_path}")
+

{mistocr-0.2.6.dist-info → mistocr-0.2.8.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mistocr
-Version: 0.2.6
+Version: 0.2.8
 Summary: Batch OCR for PDFs with heading restoration and visual content integration
 Home-page: https://github.com/franckalbinet/mistocr
 Author: Solveit

mistocr-0.2.8.dist-info/RECORD

@@ -0,0 +1,11 @@
+mistocr/__init__.py,sha256=G6Dbxq2ws-1ZAXwDD8q0KWueYtso_Y6Uyvtj8sRWsPI,22
+mistocr/_modidx.py,sha256=55k_EmMPrRmLa04qCE-_8lukJPCax66q5MALfpa8T4A,4154
+mistocr/core.py,sha256=KH5ND6ZMmETj9m9A-Ivtw5N2L-qm9vGwYgvHAzg-BsA,7218
+mistocr/pipeline.py,sha256=k5rtr9ccxTgwQAzw533iMIL9qwiCofugWv0fhotLzaI,1639
+mistocr/refine.py,sha256=yLnpqCEHRYfo1QQoAsgqk4INUjz_lYU8-tfEDgTC738,10544
+mistocr-0.2.8.dist-info/licenses/LICENSE,sha256=xV8xoN4VOL0uw9X8RSs2IMuD_Ss_a9yAbtGNeBWZwnw,11337
+mistocr-0.2.8.dist-info/METADATA,sha256=qATVQfErJIL_AbUSis3DhuM59fECxCWvgEoM15cRXf8,8416
+mistocr-0.2.8.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+mistocr-0.2.8.dist-info/entry_points.txt,sha256=HjAiHozobM-alm_6bTF-ehRr2DD3KYE9PgRngelONOY,36
+mistocr-0.2.8.dist-info/top_level.txt,sha256=LelTYnSpSXLy1Hb1m2YP3gt8luwP-I8KV0NjP_ucdSs,8
+mistocr-0.2.8.dist-info/RECORD,,

mistocr-0.2.6.dist-info/RECORD

@@ -1,11 +0,0 @@
-mistocr/__init__.py,sha256=Oz5HbwHMyE87nmwV80AZzpkJPf-wBg7eDuJr_BXZkhU,22
-mistocr/_modidx.py,sha256=55k_EmMPrRmLa04qCE-_8lukJPCax66q5MALfpa8T4A,4154
-mistocr/core.py,sha256=KH5ND6ZMmETj9m9A-Ivtw5N2L-qm9vGwYgvHAzg-BsA,7218
-mistocr/pipeline.py,sha256=k5rtr9ccxTgwQAzw533iMIL9qwiCofugWv0fhotLzaI,1639
-mistocr/refine.py,sha256=EXlCKiC16dnQfPKHUguDwypnhSQ3vK2TKdkPfkSWras,11976
-mistocr-0.2.6.dist-info/licenses/LICENSE,sha256=xV8xoN4VOL0uw9X8RSs2IMuD_Ss_a9yAbtGNeBWZwnw,11337
-mistocr-0.2.6.dist-info/METADATA,sha256=KHkqvB4eYBpPKVsj9nUg0dwmjMrHfWEcAyOCUFAHgTk,8416
-mistocr-0.2.6.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-mistocr-0.2.6.dist-info/entry_points.txt,sha256=HjAiHozobM-alm_6bTF-ehRr2DD3KYE9PgRngelONOY,36
-mistocr-0.2.6.dist-info/top_level.txt,sha256=LelTYnSpSXLy1Hb1m2YP3gt8luwP-I8KV0NjP_ucdSs,8
-mistocr-0.2.6.dist-info/RECORD,,