mistocr 0.2.7__py3-none-any.whl → 0.2.9__py3-none-any.whl

mistocr/__init__.py

@@ -1 +1 @@
-__version__ = "0.2.7"
+__version__ = "0.2.9"

mistocr/refine.py

@@ -3,10 +3,10 @@
 # AUTOGENERATED! DO NOT EDIT! File to edit: ../nbs/01_refine.ipynb.
 
 # %% auto 0
-__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']
+__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']
 
 # %% ../nbs/01_refine.ipynb 3
 from fastcore.all import *
@@ -66,6 +66,46 @@ 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")
+
+ANALYSIS STEPS (think through these before outputting corrections):
+1. For each numbered heading (e.g., "4.1", "2.a", "A.1"), identify its parent heading (e.g., "4", "2", "A")
+2. Verify the child heading is exactly one # deeper than its parent
+3. If not, mark it for correction
+
+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") MUST be shallower than child (e.g., "1.1", "2.a", "A.1")
+   - Child section MUST be exactly 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
+
+5. **Unnumbered headings in numbered documents**: If the document uses numbered headings consistently, any unnumbered heading appearing within that structure is likely misclassified bold text and should be converted to regular text (output the heading text without any # symbols in the corrected field)
+
+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), or empty string "" to remove the heading entirely
+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
@@ -220,6 +260,12 @@ 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:
@@ -236,3 +282,4 @@ 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-0.2.7.dist-info → mistocr-0.2.9.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mistocr
-Version: 0.2.7
+Version: 0.2.9
 Summary: Batch OCR for PDFs with heading restoration and visual content integration
 Home-page: https://github.com/franckalbinet/mistocr
 Author: Solveit

mistocr-0.2.9.dist-info/RECORD

@@ -0,0 +1,11 @@
+mistocr/__init__.py,sha256=F8OVhAhMXSkvvXYgZtbPn2SG1AQC3joK4yu-FrHt81Y,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=wtfS_bHlD39R8T2RbITgNX8cDCIPXI9gRrJ4y9nI_rM,12807
+mistocr-0.2.9.dist-info/licenses/LICENSE,sha256=xV8xoN4VOL0uw9X8RSs2IMuD_Ss_a9yAbtGNeBWZwnw,11337
+mistocr-0.2.9.dist-info/METADATA,sha256=n9pFeWhh-Vzd7KR7s6s3R0mdJ3xvpexujEH-0iQsRQY,8416
+mistocr-0.2.9.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+mistocr-0.2.9.dist-info/entry_points.txt,sha256=HjAiHozobM-alm_6bTF-ehRr2DD3KYE9PgRngelONOY,36
+mistocr-0.2.9.dist-info/top_level.txt,sha256=LelTYnSpSXLy1Hb1m2YP3gt8luwP-I8KV0NjP_ucdSs,8
+mistocr-0.2.9.dist-info/RECORD,,

mistocr-0.2.7.dist-info/RECORD

@@ -1,11 +0,0 @@
-mistocr/__init__.py,sha256=XHypfHSPdgXFKmOdoewn7czU670gt8InhHhzlP5j_aA,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=zSCF0gOtEKhhQTQgVq4Jh5Ujk8l8CGSO_rURhsQ09P8,10351
-mistocr-0.2.7.dist-info/licenses/LICENSE,sha256=xV8xoN4VOL0uw9X8RSs2IMuD_Ss_a9yAbtGNeBWZwnw,11337
-mistocr-0.2.7.dist-info/METADATA,sha256=eyQ65s8HsoHUUINrGiijrC8e0RzO_Wvte3rk2OLU8QY,8416
-mistocr-0.2.7.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-mistocr-0.2.7.dist-info/entry_points.txt,sha256=HjAiHozobM-alm_6bTF-ehRr2DD3KYE9PgRngelONOY,36
-mistocr-0.2.7.dist-info/top_level.txt,sha256=LelTYnSpSXLy1Hb1m2YP3gt8luwP-I8KV0NjP_ucdSs,8
-mistocr-0.2.7.dist-info/RECORD,,