mistocr 0.4.2__py3-none-any.whl → 0.4.3__py3-none-any.whl

mistocr/__init__.py

@@ -1 +1 @@
-__version__ = "0.4.2"
+__version__ = "0.4.3"

mistocr/core.py

@@ -52,8 +52,8 @@ def create_batch_entry(
     url:str, # Mistral signed URL
     cid:str=None, # Custom ID (by default using the file name without extension)
     inc_img:bool=True, # Include image in response
-    extract_header:bool=False, # Extract headers from document
-    extract_footer:bool=False # Extract footers from document
+    extract_header:bool=True, # Extract headers from document
+    extract_footer:bool=True # Extract footers from document
     ) -> dict[str, str | dict[str, str | bool]]: # Batch entry dict
     "Create a batch entry dict for OCR"
     path = Path(path)
@@ -70,7 +70,7 @@ def create_batch_entry(
             )
         )
 
-# %% ../nbs/00_core.ipynb 18
+# %% ../nbs/00_core.ipynb 19
 def prep_pdf_batch(
     path:str, # Path to PDF file, 
     cid:str=None, # Custom ID (by default using the file name without extention)
@@ -81,7 +81,7 @@ def prep_pdf_batch(
     url, c = upload_pdf(path, key)
     return create_batch_entry(path, url, cid, inc_img), c
 
-# %% ../nbs/00_core.ipynb 22
+# %% ../nbs/00_core.ipynb 23
 def submit_batch(
     entries:list[dict], # List of batch entries, 
     c:Mistral=None, # Mistral client, 
@@ -95,7 +95,7 @@ def submit_batch(
         batch_data = c.files.upload(file=dict(file_name="batch.jsonl", content=open(f.name, "rb")), purpose="batch")
     return c.batch.jobs.create(input_files=[batch_data.id], model=model, endpoint=endpoint)
 
-# %% ../nbs/00_core.ipynb 25
+# %% ../nbs/00_core.ipynb 26
 def _check_timeout(
     queued_time:int, # Time spent in QUEUED state (seconds)
     timeout:int, # Maximum allowed QUEUED time (seconds)
@@ -104,7 +104,7 @@ def _check_timeout(
     "Raise TimeoutError if job has been queued longer than timeout"
     if queued_time >= timeout: raise TimeoutError(f"Job {job_id} stayed in QUEUED for {queued_time}s, exceeding timeout of {timeout}s. Check your balance or Mistral Status.")
 
-# %% ../nbs/00_core.ipynb 26
+# %% ../nbs/00_core.ipynb 27
 def wait_for_job(
     job:dict, # Batch job from submit_batch
     c:Mistral=None, # Mistral client
@@ -123,7 +123,7 @@ def wait_for_job(
     if job.status != "SUCCESS": logger.warning(f"Job {job.id} finished with non-success status: {job.status}")
     return job
 
-# %% ../nbs/00_core.ipynb 28
+# %% ../nbs/00_core.ipynb 29
 def download_results(
     job:dict, # Job dict, 
     c:Mistral=None # Mistral client
@@ -132,7 +132,7 @@ def download_results(
     content = c.files.download(file_id=job.output_file).read().decode('utf-8')
     return [json.loads(line) for line in content.strip().split('\n') if line]
 
-# %% ../nbs/00_core.ipynb 33
+# %% ../nbs/00_core.ipynb 34
 def save_images(
     page:dict, # Page dict, 
     img_dir:str='img' # Directory to save images
@@ -143,7 +143,7 @@ def save_images(
             img_bytes = base64.b64decode(img['image_base64'].split(',')[1])
             Image.open(BytesIO(img_bytes)).save(img_dir / img['id'])
 
-# %% ../nbs/00_core.ipynb 34
+# %% ../nbs/00_core.ipynb 35
 def save_page(
     page:dict, # Page dict, 
     dst:str, # Directory to save page
@@ -155,7 +155,7 @@ def save_page(
         img_dir.mkdir(exist_ok=True)
         save_images(page, img_dir)
 
-# %% ../nbs/00_core.ipynb 36
+# %% ../nbs/00_core.ipynb 37
 def save_pages(
     ocr_resp:dict, # OCR response, 
     dst:str, # Directory to save pages, 
@@ -168,7 +168,7 @@ def save_pages(
     for page in ocr_resp['pages']: save_page(page, dst, img_dir)
     return dst
 
-# %% ../nbs/00_core.ipynb 42
+# %% ../nbs/00_core.ipynb 43
 def _get_paths(path:str) -> list[Path]:
     "Get list of PDFs from file or folder"
     path = Path(path)
@@ -179,7 +179,7 @@ def _get_paths(path:str) -> list[Path]:
         return pdfs
     raise ValueError(f"Path not found: {path}")
 
-# %% ../nbs/00_core.ipynb 43
+# %% ../nbs/00_core.ipynb 44
 def _prep_batch(pdfs:list[Path], inc_img:bool=True, key:str=None) -> tuple[list[dict], Mistral]:
     "Prepare batch entries for list of PDFs"
     entries, c = [], None
@@ -188,7 +188,7 @@ def _prep_batch(pdfs:list[Path], inc_img:bool=True, key:str=None) -> tuple[list[
         entries.append(entry)
     return entries, c
 
-# %% ../nbs/00_core.ipynb 44
+# %% ../nbs/00_core.ipynb 45
 def _run_batch(entries:list[dict], c:Mistral, poll_interval:int=2) -> list[dict]:
     "Submit batch, wait for completion, and download results"
     job = submit_batch(entries, c)
@@ -196,7 +196,7 @@ def _run_batch(entries:list[dict], c:Mistral, poll_interval:int=2) -> list[dict]
     if job.status != 'SUCCESS': raise Exception(f"Job failed with status: {job.status}")
     return download_results(job, c)
 
-# %% ../nbs/00_core.ipynb 45
+# %% ../nbs/00_core.ipynb 46
 def ocr_pdf(
     path:str, # Path to PDF file or folder,
     dst:str='md', # Directory to save markdown pages, 
@@ -210,7 +210,7 @@ def ocr_pdf(
     results = _run_batch(entries, c, poll_interval)
     return L([save_pages(r['response']['body'], dst, r['custom_id']) for r in results])
 
-# %% ../nbs/00_core.ipynb 52
+# %% ../nbs/00_core.ipynb 53
 def read_pgs(
     path:str, # OCR output directory, 
     join:bool=True # Join pages into single string
@@ -221,7 +221,7 @@ def read_pgs(
     contents = L([p.read_text() for p in pgs])
     return '\n\n'.join(contents) if join else contents
 
-# %% ../nbs/00_core.ipynb 59
+# %% ../nbs/00_core.ipynb 60
 def subset_pdf(
     path:str, # Path to PDF file
     start:int=1, # Start page (1-based)

{mistocr-0.4.2.dist-info → mistocr-0.4.3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mistocr
-Version: 0.4.2
+Version: 0.4.3
 Summary: Batch OCR for PDFs with heading restoration and visual content integration
 Home-page: https://github.com/franckalbinet/mistocr
 Author: Solveit

mistocr-0.4.3.dist-info/RECORD

@@ -0,0 +1,11 @@
+mistocr/__init__.py,sha256=Nyg0pmk5ea9-SLCAFEIF96ByFx4-TJFtrqYPN-Zn6g4,22
+mistocr/_modidx.py,sha256=LyFez7ndKOXQpF0unhg1imCrW7xcUwO106W82ttVnnk,4366
+mistocr/core.py,sha256=DQzJqbZqdSNLNvWjuXGQx9Z1pha00s5dWuBds3dHpno,9505
+mistocr/pipeline.py,sha256=n8AHIHGZBXYy_k7LtEBZSiTL6HClT84-7K4QlTjOLvo,2107
+mistocr/refine.py,sha256=Q14DhUUsT5FLMxP9oIJ2TGQ3qbxe7ulXfRMPKpsd4Wo,13232
+mistocr-0.4.3.dist-info/licenses/LICENSE,sha256=xV8xoN4VOL0uw9X8RSs2IMuD_Ss_a9yAbtGNeBWZwnw,11337
+mistocr-0.4.3.dist-info/METADATA,sha256=xflyT5mn1mEOmzBv4vvGhPazaHc6oq6jCe9A7mPCpT0,9011
+mistocr-0.4.3.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
+mistocr-0.4.3.dist-info/entry_points.txt,sha256=HjAiHozobM-alm_6bTF-ehRr2DD3KYE9PgRngelONOY,36
+mistocr-0.4.3.dist-info/top_level.txt,sha256=LelTYnSpSXLy1Hb1m2YP3gt8luwP-I8KV0NjP_ucdSs,8
+mistocr-0.4.3.dist-info/RECORD,,

mistocr-0.4.2.dist-info/RECORD

@@ -1,11 +0,0 @@
-mistocr/__init__.py,sha256=6hfVa12Q-nXyUEXr6SyKpqPEDJW6vlRHyPxlA27PfTs,22
-mistocr/_modidx.py,sha256=LyFez7ndKOXQpF0unhg1imCrW7xcUwO106W82ttVnnk,4366
-mistocr/core.py,sha256=nIwqszvMMvlLgYtweIq4hN1UsA_-P5K6k9YE1BIQn2g,9507
-mistocr/pipeline.py,sha256=n8AHIHGZBXYy_k7LtEBZSiTL6HClT84-7K4QlTjOLvo,2107
-mistocr/refine.py,sha256=Q14DhUUsT5FLMxP9oIJ2TGQ3qbxe7ulXfRMPKpsd4Wo,13232
-mistocr-0.4.2.dist-info/licenses/LICENSE,sha256=xV8xoN4VOL0uw9X8RSs2IMuD_Ss_a9yAbtGNeBWZwnw,11337
-mistocr-0.4.2.dist-info/METADATA,sha256=lfBxmqi3TP9XSvTY_1qhSdMfjH0fr9IXzeo0-sgE2eo,9011
-mistocr-0.4.2.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
-mistocr-0.4.2.dist-info/entry_points.txt,sha256=HjAiHozobM-alm_6bTF-ehRr2DD3KYE9PgRngelONOY,36
-mistocr-0.4.2.dist-info/top_level.txt,sha256=LelTYnSpSXLy1Hb1m2YP3gt8luwP-I8KV0NjP_ucdSs,8
-mistocr-0.4.2.dist-info/RECORD,,