natural-pdf 0.2.1.dev0__py3-none-any.whl → 0.2.3__py3-none-any.whl

natural_pdf/tables/result.py

@@ -44,6 +44,7 @@ class TableResult(Sequence):
         header: Union[str, int, List[int], None] = "first",
         index_col=None,
         skip_repeating_headers=None,
+        keep_blank: bool = False,
         **kwargs,
     ):
         """Convert to *pandas* DataFrame.
@@ -52,11 +53,22 @@ class TableResult(Sequence):
         ----------
         header : "first" | int | list[int] | None, default "first"
             • "first" – use row 0 as column names.\n            • int       – use that row index.\n            • list[int] – multi-row header.\n            • None/False– no header.
+
+            Note: If the header row has a different number of columns than the
+            body rows, the method will automatically fall back to header=None
+            to prevent pandas errors. This commonly occurs when headers are
+            merged into a single cell during PDF extraction.
+
         index_col : same semantics as pandas, forwarded.
         skip_repeating_headers : bool, optional
             Whether to remove body rows that exactly match the header row(s).
             Defaults to True when header is truthy, False otherwise.
             Useful for PDFs where headers repeat throughout the table body.
+        keep_blank : bool, default False
+            Whether to preserve empty strings ('') as-is in the DataFrame.
+            When False (default), empty cells become pd.NA for better pandas integration
+            with numerical operations and missing data functions (.dropna(), .fillna(), etc.).
+            When True, empty strings are preserved as empty strings.
         **kwargs  : forwarded to :pyclass:`pandas.DataFrame`.
         """
         try:
@@ -112,7 +124,32 @@ class TableResult(Sequence):
                 # Could add logging here if desired
                 pass
 
+        # Check for header/body column count mismatch and fallback to no header
+        if hdr is not None and body:
+            # Get the maximum number of columns from all body rows
+            # This handles cases where some rows have different column counts
+            max_cols = max(len(row) for row in body) if body else 0
+
+            # Check if header matches the maximum column count
+            header_cols = 0
+            if isinstance(hdr, list) and not isinstance(hdr[0], list):
+                # Single header row
+                header_cols = len(hdr)
+            elif isinstance(hdr, list) and len(hdr) > 0 and isinstance(hdr[0], list):
+                # Multi-row header - check first header row
+                header_cols = len(hdr[0])
+
+            if header_cols != max_cols:
+                # Column count mismatch - fallback to no header
+                hdr = None
+                body = self._rows  # Use all rows as body
+
         df = pd.DataFrame(body, columns=hdr)
+
+        # Convert empty strings to NaN by default
+        if not keep_blank:
+            df = df.replace("", pd.NA)
+
         if index_col is not None and not df.empty:
             df.set_index(
                 df.columns[index_col] if isinstance(index_col, int) else index_col, inplace=True

{natural_pdf-0.2.1.dev0.dist-info → natural_pdf-0.2.3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: natural-pdf
-Version: 0.2.1.dev0
+Version: 0.2.3
 Summary: A more intuitive interface for working with PDFs
 Author-email: Jonathan Soma <jonathan.soma@gmail.com>
 License-Expression: MIT
@@ -14,7 +14,7 @@ License-File: LICENSE
 Requires-Dist: scikit-learn
 Requires-Dist: markdown
 Requires-Dist: pandas
-Requires-Dist: pdfplumber
+Requires-Dist: pdfplumber>=0.11.7
 Requires-Dist: colormath2
 Requires-Dist: pillow
 Requires-Dist: colour

{natural_pdf-0.2.1.dev0.dist-info → natural_pdf-0.2.3.dist-info}/RECORD

@@ -2,7 +2,7 @@ natural_pdf/__init__.py,sha256=N4pR0LbuPEnUYFZqbdVqc_FGKldgwPQc1wjJhYKTBBM,3417
 natural_pdf/cli.py,sha256=SkPwhhMM-GhLsj3O1n1Agxz4KOxcZ08sj8hVQSFJB5c,4064
 natural_pdf/text_mixin.py,sha256=eFCiHj6Okcw3aum4955BepcI2NPRalkf9UFFVTc_H30,4012
 natural_pdf/analyzers/__init__.py,sha256=3XGoNq3OgiVkZP7tOdeP5XVUl7fDgyztdA8DlOcMLXg,1138
-natural_pdf/analyzers/guides.py,sha256=N8fetR3jrDXzeHtIlbxg8BEbthB_lS0L8yhzVXHqiGQ,143245
+natural_pdf/analyzers/guides.py,sha256=9FUbxk4XBOyktXgq9q5-bB949JFrzT1kBPikg2ENoIw,150032
 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
@@ -23,28 +23,29 @@ natural_pdf/analyzers/layout/yolo.py,sha256=2Iz2-WsMy--ftkZQ8j5PGqp_1fTD7Mskl2kN
 natural_pdf/classification/manager.py,sha256=BaqBL9GeMvYgoJsiQeI2J8aUKQ5Qxu_ELRvmCWquld8,22172
 natural_pdf/classification/mixin.py,sha256=CXygXXhe_qx1563SmIjiu4uSnZkxCkuRR4fGvLokS2w,9416
 natural_pdf/classification/results.py,sha256=5ha77CxK0GYwkBMJbvUBZkBjsL5GpOveIZDK9nO4j8I,3239
-natural_pdf/collections/mixins.py,sha256=u4KtnlUZZYQ74e0OXAniOv9RtuA6FhwBxsLMJLjdbpQ,5169
+natural_pdf/collections/mixins.py,sha256=Se2C5AcpP9B5E0d0pIrey6-f_P32tAXTK4M7666MNj0,5688
 natural_pdf/core/__init__.py,sha256=QC8H4M3KbXwMFiQORZ0pdPlzx1Ix6oKKQSS7Ib2KEaA,38
 natural_pdf/core/element_manager.py,sha256=DRZvntd99wjXy6KeDjCq5uRhjMftZop9QklOZqlUH8M,55349
-natural_pdf/core/highlighting_service.py,sha256=k_SMCINeK4aUwfQLmaiyipCPL8vv33ibrCyqtlni8Bc,67921
-natural_pdf/core/page.py,sha256=nQDUR4eKsUhPmEnofjmJRPITQ1RJoK3ITC0Lrtt4AHw,135510
-natural_pdf/core/page_collection.py,sha256=9ff7IfO04bUkJCBZv__Z9G8A-NY7mR3OujVl54lH-FE,50985
+natural_pdf/core/highlighting_service.py,sha256=7on8nErhi50CEH2L4XzGIZ6tIqZtMzmmFlp-2lmwnYE,68856
+natural_pdf/core/page.py,sha256=4-il2WPMVX4hNSgQ5P6yLc1-3jXfi73WCrpF9912ct4,142472
+natural_pdf/core/page_collection.py,sha256=hEeXs_fzB73XZ8ZkHz2kIuSgBYcVYydvGMMdGuB1rvw,52486
+natural_pdf/core/page_groupby.py,sha256=550ME6kd-h-2u75oUIIIqTYsmh8VvdQO1nXXioL8J6A,7378
 natural_pdf/core/pdf.py,sha256=q54DyhXwAS_zAmsBd3PsCezu1wyQOYmGmB3iKfP8gAM,101884
 natural_pdf/core/pdf_collection.py,sha256=8tM0qVWS1L5Hwv5cXuZ2X8znAYOjKmlERX62bksDlJU,30144
-natural_pdf/core/render_spec.py,sha256=j77UrHA_g_e0RbAyn-4hkjFtqm_oaTe5KRd_Ii9izf4,12243
+natural_pdf/core/render_spec.py,sha256=3GTfnlv8JKzePrruLq_dNr3HFeWMVcZT2fwWmJN44NI,14456
 natural_pdf/describe/__init__.py,sha256=kIV7ORmWWB1SAur7nK2aAwR-wHqSedhKfUsaUl4hG0A,586
 natural_pdf/describe/base.py,sha256=Of9WVo9XuShXoeyJr0RN2CpLhF_CeiOjazl-or53RKU,18173
 natural_pdf/describe/elements.py,sha256=JicXC9SJmmasqxalpCXA47-kVwv-6JnR3Xiu778aNHM,12634
 natural_pdf/describe/mixin.py,sha256=rkX14aGrSz7Jvxx8Rbxv3eSfbO-_29DipwpstrV2pDQ,3109
 natural_pdf/describe/summary.py,sha256=cfT4ZQkeatCDAOwWPwhtEVXisNgk6E57fAXAnoRysSU,7645
 natural_pdf/elements/__init__.py,sha256=ICNikmLeIEuSYypz-KnkBn8xR1hR7rge4hsa1KLkyWY,42
-natural_pdf/elements/base.py,sha256=jEBw5cq4mzgOYeEBrWPml2RBuVmOnwBNA4nTd7pLmMI,52292
-natural_pdf/elements/element_collection.py,sha256=av2YKTxEB5lHYqw1A6aYoN-Uef2qzT9z6ibBAbJMPo4,101322
+natural_pdf/elements/base.py,sha256=xXdNV1_gt4T_V_4m6qJDieWiysvJxUBhSEEAJzMOzqo,55094
+natural_pdf/elements/element_collection.py,sha256=slCUnOT04sNOTjSGgmhjcCKKPVPtdDPwU7PX1ebzGMw,101342
 natural_pdf/elements/image.py,sha256=zu-P2Y8fRoEXf6IeZU0EYRWsgZ6I_a5vy1FA3VXTGkQ,1424
 natural_pdf/elements/line.py,sha256=TFn7KXjPT_jUQyQyabU0F7XYU4dC-qadwodJMZF4DCU,3844
 natural_pdf/elements/rect.py,sha256=0lNkVkPkvbRbrFED856RXoUcTcDkeeOIs5xldKGAQT8,3324
-natural_pdf/elements/region.py,sha256=PoT4e2s0gPkMa2Px0LjkThi-Jc8O0_ebl6U7UYADAQk,155289
-natural_pdf/elements/text.py,sha256=IyyU3G4F3OzNZ4Oo0BTK_Wq0p0xFj5EYBWNVL4SZ-BQ,20492
+natural_pdf/elements/region.py,sha256=Onok5VzmF1CvMCa3UGLUszCuhL-CCGk_IgtSUDva-Cc,155314
+natural_pdf/elements/text.py,sha256=829uSJv9E-8cC6T6iR_Va7Xtv54pJoyRN78fq4NN1d4,20687
 natural_pdf/export/mixin.py,sha256=L1q3MIEFWuvie4j4_EmW7GT3NerbZ1as0XMUoqTS7gM,5083
 natural_pdf/exporters/__init__.py,sha256=QffoARekR6WzXEd05oxOytly4qPdBizuIF-SUkeFpig,643
 natural_pdf/exporters/base.py,sha256=379sioW_hbkGb21sEVuJhbkkDO5MFsFtTUNO5TgG2YU,2101
@@ -56,8 +57,8 @@ natural_pdf/exporters/searchable_pdf.py,sha256=7RDNTV2jK5b5PhZz-v-kpYGTDCXu8FBgX
 natural_pdf/exporters/data/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 natural_pdf/exporters/data/pdf.ttf,sha256=x4RUIJJaI9iO2DCmOVe4r4Wmao2vjZ_JDoQ2c7LvGlk,572
 natural_pdf/exporters/data/sRGB.icc,sha256=KpLUuuRQt22LCqQhk9-XTXX2Jzjs6_dPAcXnWxKpV5Y,6922
-natural_pdf/extraction/manager.py,sha256=sASPJZ5cWFsl8A4PyTjg2yqkyC00tRl6glfoFA6HcsM,4979
-natural_pdf/extraction/mixin.py,sha256=ck2e48BYZg5RNderNE0QST6RSn2D6mIZYBw91nMSgp8,24970
+natural_pdf/extraction/manager.py,sha256=R-wGe9PGky6r4BTSUPMXf3N2l12kycku3GJKEd45eFU,4701
+natural_pdf/extraction/mixin.py,sha256=dBcp96R8zMQqaRHiB8vpyad8GR89gv5RPXlr8Mt0ais,25427
 natural_pdf/extraction/result.py,sha256=PDaCCN2LQBbHsZy0_lrQ0ROeMsnmH1WRoXWOjk9M2o4,1825
 natural_pdf/flows/__init__.py,sha256=cUN4A8hTDLZSRr4PO2W_lR4z6hWpbNG8Seox-IIcrLU,277
 natural_pdf/flows/collections.py,sha256=ErkHWdX6W_y1SjkcA_bGM0uUYRGPWWpRkHip6LHpej0,25740
@@ -84,9 +85,9 @@ natural_pdf/search/search_options.py,sha256=sq_e8_jSROicD94b_xtDtLnjEr_Zsy4icjzP
 natural_pdf/search/search_service_protocol.py,sha256=u8pbuWP96fnQEe6mnreY9DrdiDAHP6ZCY7phvSbFlP8,6697
 natural_pdf/search/searchable_mixin.py,sha256=hqQ_AuID5eTGRCtKYdFLZ1zF35y73uk3x1M1VW9Il8U,23514
 natural_pdf/selectors/__init__.py,sha256=oZGeqSv53EqmIZOhcnawuaGGlRg1h79vArXuZCWKm4A,123
-natural_pdf/selectors/parser.py,sha256=uWo0K4uWJFbD4kTXz9fOcPwEjs7cGR9Mfpm1jm7qKUM,38824
+natural_pdf/selectors/parser.py,sha256=pw0M8ICKPMOzZPzWpLsQMG_lnl8PewGIdIG3ciukabk,38877
 natural_pdf/tables/__init__.py,sha256=sCvCGbGsL6BiqlNxAYfVv003bIDLI11FmjHhaWfcU6w,104
-natural_pdf/tables/result.py,sha256=lfhLs5OxZ2IRLNndb8zjOQBk1SPjHx4KePzI7GlRkMg,5478
+natural_pdf/tables/result.py,sha256=1pcelNZvOb6Anlwj08Z1XU-YK1ihlCsLpYMRA3Zc4JM,7242
 natural_pdf/templates/__init__.py,sha256=jYBxzfi73vew0f6yhIh1MlRxw4F_TVN2hKQR0YXOFe0,20
 natural_pdf/utils/__init__.py,sha256=s3M8FggaK1P3EBYn6R_-HgSDjNc9C73gyKe1hihtNWg,43
 natural_pdf/utils/bidi_mirror.py,sha256=jJEES0xDrMfo5Me8kHMxHv4COS51PitnYi2EvKv3HCE,1151
@@ -101,14 +102,14 @@ natural_pdf/utils/text_extraction.py,sha256=CCwPTmMoTgtQt2P00X_ADIf6ZGNfxvjCO9FO
 natural_pdf/utils/visualization.py,sha256=zhZEHgYnZFuX7YxTHXF8Y3D97uHp2beTKMaC-JkCFwk,22364
 natural_pdf/widgets/__init__.py,sha256=QTVaUmsw__FCweFYZebwPssQxxUFUMd0wpm_cUbGZJY,181
 natural_pdf/widgets/viewer.py,sha256=KW3JogdR2TMg2ECUMYp8hwd060hfg8EsYBWxb5IEzBY,24942
-natural_pdf-0.2.1.dev0.dist-info/licenses/LICENSE,sha256=9zfwINwJlarbDmdh6iJV4QUG54QSJlSAUcnC1YiC_Ns,1074
+natural_pdf-0.2.3.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=RjAqeE3YS1r_7qTWkY6Ng5YMbb6MXJXfXX6LoVjg_xQ,13035
+optimization/performance_analysis.py,sha256=JBXnR9hc7Ix7YCnt3EJPSpsyqIUgKsc7GEffQ_TDCBk,13033
 optimization/test_cleanup_methods.py,sha256=PmLOL4MRgvV0j_DW9W1TS8MsGGgu57QCuq6_5y7zK3s,6209
 optimization/test_memory_fix.py,sha256=A3knK74fNhvHknDbLhbTmA276x1ifl-3ivJ_7BhVSTI,6170
 tools/bad_pdf_eval/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-tools/bad_pdf_eval/analyser.py,sha256=bKUT3muP3ESE5i1D8sGyAS5tMzFMcq-i-xD_ZeUxYhY,13692
+tools/bad_pdf_eval/analyser.py,sha256=oqSTo3NLyignp_XdCO9_SRCUUXMU8lfgDavKYZYNxws,13690
 tools/bad_pdf_eval/collate_summaries.py,sha256=L_YsdiqmwGIHYWTVJqo6gyazyn3GIQgpfGGKk8uwckk,5159
 tools/bad_pdf_eval/compile_attempts_markdown.py,sha256=ArFDZaSa9dz0ez0lsNlbUSK4hbvB3___DlfwqPEAZpY,4359
 tools/bad_pdf_eval/eval_suite.py,sha256=zcapsGwO-VJ2OupJnPYKbrkzvzdGdoh2DZPK19bfkQg,4450
@@ -118,8 +119,8 @@ 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-0.2.1.dev0.dist-info/METADATA,sha256=A8hOXH7KhQgMTCKN0keud9u2m9V-_RnWPWjaSBo7Luc,6956
-natural_pdf-0.2.1.dev0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-natural_pdf-0.2.1.dev0.dist-info/entry_points.txt,sha256=1R_KMv7g60UBBpRqGfw7bppsMNGdayR-iJlb9ohEk_8,81
-natural_pdf-0.2.1.dev0.dist-info/top_level.txt,sha256=80t0F2ZeX4vN4Ke5iTflcOk_PN_0USn33ha3X6X86Ik,36
-natural_pdf-0.2.1.dev0.dist-info/RECORD,,
+natural_pdf-0.2.3.dist-info/METADATA,sha256=lyx6Cx1xPGhy-p1m0wRfTvv4zSJ4ZJnNo7DeGQZ99yU,6959
+natural_pdf-0.2.3.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+natural_pdf-0.2.3.dist-info/entry_points.txt,sha256=1R_KMv7g60UBBpRqGfw7bppsMNGdayR-iJlb9ohEk_8,81
+natural_pdf-0.2.3.dist-info/top_level.txt,sha256=80t0F2ZeX4vN4Ke5iTflcOk_PN_0USn33ha3X6X86Ik,36
+natural_pdf-0.2.3.dist-info/RECORD,,

optimization/performance_analysis.py

@@ -211,7 +211,7 @@ class PDFPerformanceTester:
 
             for resolution in resolutions:
                 try:
-                    img = page.to_image(resolution=resolution)
+                    img = page.render(resolution=resolution)
 
                     self.profiler.take_snapshot(
                         f"image_{resolution}dpi_{i+1}",

tools/bad_pdf_eval/analyser.py

@@ -39,7 +39,7 @@ class BadPDFAnalyzer:
     # ---------------------------------------------------------------------
     def _save_page_image(self, page, page_num: int) -> Path:
         """Render and save page image as high-quality JPG."""
-        img: Image.Image = page.to_image(resolution=self.resolution)
+        img: Image.Image = page.render(resolution=self.resolution)
         if img.mode != "RGB":
             img = img.convert("RGB")
         img_path = self.output_dir / f"page_{page_num:04d}.jpg"