natural-pdf 0.2.19__py3-none-any.whl → 0.2.20__py3-none-any.whl

natural_pdf/analyzers/guides.py

@@ -943,7 +943,7 @@ class GuidesList(UserList):
 
     def from_headers(
         self,
-        headers: Union["ElementCollection", List["Element"]],
+        headers: Union["ElementCollection", List["Element"], List[str]],
         obj: Optional[Union["Page", "Region"]] = None,
         method: Literal["min_crossings", "seam_carving"] = "min_crossings",
         min_width: Optional[float] = None,
@@ -960,7 +960,10 @@ class GuidesList(UserList):
         between headers that minimize text crossings, regardless of text alignment.
 
         Args:
-            headers: Column header elements (ElementCollection or list of Elements)
+            headers: Column header elements. Can be:
+                - ElementCollection: collection of header elements
+                - List[Element]: list of header elements
+                - List[str]: list of header text to search for
             obj: Page/Region to analyze (uses parent's context if None)
             method: Detection method:
                 - 'min_crossings': Fast vector-based minimum intersection count
@@ -980,6 +983,9 @@ class GuidesList(UserList):
             headers = page.find_all('text[size=16]')
             guides.vertical.from_headers(headers)
 
+            # From header text strings
+            guides.vertical.from_headers(["Statute", "Description", "Level", "Repeat"])
+
             # With width constraints
             guides.vertical.from_headers(headers, min_width=50, max_width=200)
 
@@ -997,6 +1003,24 @@ class GuidesList(UserList):
         # Convert headers to list if ElementCollection
         if hasattr(headers, "elements"):
             header_elements = list(headers.elements)
+        # Check if headers is a list of strings
+        elif isinstance(headers, list) and headers and isinstance(headers[0], str):
+            # Find elements for each header text with exact matching
+            header_elements = []
+            for header_text in headers:
+                # Find all text elements and filter for exact match
+                all_text = target_obj.find_all("text")
+                exact_matches = [elem for elem in all_text if elem.extract_text() == header_text]
+
+                if exact_matches:
+                    # Use the first exact match
+                    header_elements.append(exact_matches[0])
+                else:
+                    logger.warning(f"Could not find header text: {header_text}")
+
+            if not header_elements:
+                logger.warning("No header elements found from provided text strings")
+                return self._parent
         else:
             header_elements = list(headers)
 

{natural_pdf-0.2.19.dist-info → natural_pdf-0.2.20.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: natural-pdf
-Version: 0.2.19
+Version: 0.2.20
 Summary: A more intuitive interface for working with PDFs
 Author-email: Jonathan Soma <jonathan.soma@gmail.com>
 License-Expression: MIT

{natural_pdf-0.2.19.dist-info → natural_pdf-0.2.20.dist-info}/RECORD

@@ -3,7 +3,7 @@ natural_pdf/cli.py,sha256=0zO9ZoRiP8JmyGBaVavrMATnvbARWTl7WD2PEefu9BM,4061
 natural_pdf/judge.py,sha256=mRPJfdIkkL_Y6uQXnb3Wtrna04XlhPrDvxPrDiVevH4,58838
 natural_pdf/text_mixin.py,sha256=eFCiHj6Okcw3aum4955BepcI2NPRalkf9UFFVTc_H30,4012
 natural_pdf/analyzers/__init__.py,sha256=3XGoNq3OgiVkZP7tOdeP5XVUl7fDgyztdA8DlOcMLXg,1138
-natural_pdf/analyzers/guides.py,sha256=BqFgt-bRSOkEoFCvNsYyY8j__00X-8DJ_TLb2Hx9qsQ,202430
+natural_pdf/analyzers/guides.py,sha256=SCliIk36Bu-7rMwp0K_XO0MtTVokXvxre4FNysYowiE,203626
 natural_pdf/analyzers/shape_detection_mixin.py,sha256=mgpyJ4jIulz9l9HCqThabJIsLSrXh9BB2AmLxUoHmw0,62584
 natural_pdf/analyzers/text_options.py,sha256=qEkDaYWla0rIM_gszEOsu52q7C_dAfV81P2HLJZM2sw,3333
 natural_pdf/analyzers/text_structure.py,sha256=3WWusi-BI0krUnJxB05DD6XmKj5qRNvQBqH7zOQGm1M,28451
@@ -119,7 +119,7 @@ natural_pdf/vision/similarity.py,sha256=HWmXDBNLSOlRWH-_1K3FVR7tSsRuMFqXZwrVhhg2
 natural_pdf/vision/template_matching.py,sha256=91XQt5tp-vmcMX_4b2Bz-YwIAlb-hc8E5ih_qAHQuCk,7145
 natural_pdf/widgets/__init__.py,sha256=QTVaUmsw__FCweFYZebwPssQxxUFUMd0wpm_cUbGZJY,181
 natural_pdf/widgets/viewer.py,sha256=KW3JogdR2TMg2ECUMYp8hwd060hfg8EsYBWxb5IEzBY,24942
-natural_pdf-0.2.19.dist-info/licenses/LICENSE,sha256=9zfwINwJlarbDmdh6iJV4QUG54QSJlSAUcnC1YiC_Ns,1074
+natural_pdf-0.2.20.dist-info/licenses/LICENSE,sha256=9zfwINwJlarbDmdh6iJV4QUG54QSJlSAUcnC1YiC_Ns,1074
 optimization/memory_comparison.py,sha256=0i_foFSRmppj-fY069qjwH36s_zkx-1L2ASAAlepWzA,6541
 optimization/pdf_analyzer.py,sha256=HjrmTgu2qchxPeDckc5kjgxppGwd40UESrYS9Myj7pY,19352
 optimization/performance_analysis.py,sha256=JBXnR9hc7Ix7YCnt3EJPSpsyqIUgKsc7GEffQ_TDCBk,13033
@@ -172,8 +172,8 @@ tools/bad_pdf_eval/llm_enrich.py,sha256=mCh4KGi1HmIkzGjj5rrHz1Osd7sEX1IZ_FW08H1t
 tools/bad_pdf_eval/llm_enrich_with_retry.py,sha256=XUtPF1hUvqd3frDXT0wDTXoonuAivhjM5vgFdZ-tm0A,9373
 tools/bad_pdf_eval/reporter.py,sha256=e1g__mkSB4q02p3mGWOwMhvFs7F2HJosNBxup0-LkyU,400
 tools/bad_pdf_eval/utils.py,sha256=hR95XQ7qf7Cu6BdyX0L7ggGVx-ah5sK0jHWblTJUUic,4896
-natural_pdf-0.2.19.dist-info/METADATA,sha256=vtMsWwMW9cR2LdQhdDFhDG4WWIkctrT7_3P7klvyJ-8,6960
-natural_pdf-0.2.19.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-natural_pdf-0.2.19.dist-info/entry_points.txt,sha256=1R_KMv7g60UBBpRqGfw7bppsMNGdayR-iJlb9ohEk_8,81
-natural_pdf-0.2.19.dist-info/top_level.txt,sha256=ZDKhxE_tg508o9BpagsjCGcI8GY4cF_8bg0e0IaLsPI,41
-natural_pdf-0.2.19.dist-info/RECORD,,
+natural_pdf-0.2.20.dist-info/METADATA,sha256=zryX6u3cPk4iuwz_leohWyd-i0SdvM_hr-h1APjffWQ,6960
+natural_pdf-0.2.20.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+natural_pdf-0.2.20.dist-info/entry_points.txt,sha256=1R_KMv7g60UBBpRqGfw7bppsMNGdayR-iJlb9ohEk_8,81
+natural_pdf-0.2.20.dist-info/top_level.txt,sha256=ZDKhxE_tg508o9BpagsjCGcI8GY4cF_8bg0e0IaLsPI,41
+natural_pdf-0.2.20.dist-info/RECORD,,