raw-docx 0.7.0__py3-none-any.whl → 0.8.0__py3-none-any.whl

raw_docx/__info__.py

@@ -1 +1 @@
-__package_version__ = "0.7.0"
+__package_version__ = "0.8.0"

raw_docx/raw_document.py

@@ -22,7 +22,7 @@ class RawDocument:
         return self.sections[-1]
 
     def section_by_ordinal(self, ordinal: int) -> RawSection:
-        if 1 >= ordinal <= len(self.sections):
+        if 1 <= ordinal <= len(self.sections):
             return self.sections[ordinal - 1]
         else:
             return None

raw_docx/raw_docx.py

@@ -144,7 +144,10 @@ class RawDocx:
                 else:
                     h_span = 1
                     v_span = 1
-                first = r_index == cell._tc.top and c_index == cell._tc.left
+                if cell._tc is not None:
+                    first = r_index == cell._tc.top and c_index == cell._tc.left
+                else:
+                    first = r_index == 0 and c_index == 0
                 target_cell = RawTableCell(h_span, v_span, first)
                 target_row.add(target_cell)
                 for block_item in self._iter_block_items(cell):
@@ -207,18 +210,27 @@ class RawDocx:
         list_level = paragraph._p.xpath("./w:pPr/w:numPr/w:ilvl/@w:val")
         return int(str(list_level[0])) if list_level else 0
 
-    def _is_heading(self, text):
-        if re.match(r"^\d\dHeading \d", text):
-            try:
-                level = int(text[0:2])
-                return True, level
-            except Exception:
-                return True, 0
-        if re.match(r"^Heading \d", text):
+    def _is_heading(self, text) -> tuple[bool, int]:
+        """
+        Extract heading level from text containing "Heading <N>" pattern.
+
+        Args:
+            text: Text to analyze for heading pattern
+
+        Returns:
+            tuple[bool, int]: (success, level) where success indicates if heading
+            pattern was found and level is the extracted integer value
+        """
+        if not text:
+            return False, 0
+
+        # Look for "Heading <N>" pattern where <N> is one or more digits
+        match = re.search(r"Heading\s+(\d+)", text, re.IGNORECASE)
+        if match:
             try:
-                level = int(text[8])
+                level = int(match.group(1))
                 return True, level
-            except Exception:
+            except (ValueError, IndexError):
                 return True, 0
         return False, 0
 

{raw_docx-0.7.0.dist-info → raw_docx-0.8.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: raw_docx
-Version: 0.7.0
+Version: 0.8.0
 Summary: A package for processing and analyzing raw document formats
 Home-page: https://github.com/daveih/raw_docx
 Author: Dave Iberson-Hurst
@@ -17,8 +17,8 @@ Classifier: Programming Language :: Python :: 3.11
 Requires-Python: >=3.8
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: python-docx
-Requires-Dist: simple_error_log
+Requires-Dist: python-docx==1.1.2
+Requires-Dist: simple_error_log==0.6.0
 Dynamic: author
 Dynamic: classifier
 Dynamic: description
@@ -38,4 +38,4 @@ Simple package to build on top of python-docx to assist in the handling of word
 Build as a normal package
 
 - Build with `python3 -m build --sdist --wheel`
-- Upload to pypi.org using `twine upload dist/* `
+- Upload to pypi.org using `twine upload dist/*`

{raw_docx-0.7.0.dist-info → raw_docx-0.8.0.dist-info}/RECORD

@@ -1,7 +1,7 @@
-raw_docx/__info__.py,sha256=JyImHLdD9tOVOKODJRy37_fBqVJ9Nup6yLR4gOOCtz8,30
+raw_docx/__info__.py,sha256=onU36pd8pPYPNlWn6QKkq5qJkOLC2_M4_UeggrLuh-A,30
 raw_docx/__init__.py,sha256=FE5cpoCK1EVhpz3LiOOs43l027PcuJN5RljdW0UWON0,591
-raw_docx/raw_document.py,sha256=VLx0-Z9jGwdYHMU227AKaT8UDRY_OHD7b2BRuw71x6M,2340
-raw_docx/raw_docx.py,sha256=VhmwkP1kO5Bjr1WnfCyJE6JL728ZEHvStlQ78VuFFxQ,10379
+raw_docx/raw_document.py,sha256=hUrnf6QZs9-yysnz1UmYZCYvhqdyPi3v2i-t5mu5KsI,2340
+raw_docx/raw_docx.py,sha256=huZzOyfzkhAILa6MurNO6qpye4gy39FljT9m40rrAX4,10850
 raw_docx/raw_image.py,sha256=IUUETwW73-guaa_v-cHpfw0_z69u9wfvEk7adm9hHJQ,1506
 raw_docx/raw_list.py,sha256=bhssQX_oVf8uBmUbcrCIzIJ8pCvdEtdHOAQBNH0EEQQ,2282
 raw_docx/raw_list_item.py,sha256=4Mn3rmnpXppJGAxk-9StLD60wszk5igg-TIbBz8sKW4,623
@@ -13,8 +13,8 @@ raw_docx/raw_table_cell.py,sha256=pXe7FCfEmbqdktBGfkDrvMsbEie8FaGNQbRl_ooms0Q,18
 raw_docx/raw_table_row.py,sha256=m8SoLyVlKLjd_Vqa_U79A2wi8Wout8spgyusqJm79Kc,1297
 raw_docx/docx/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 raw_docx/docx/docx_paragraph.py,sha256=DPFzCG26y-6teL3KDnC_Ihmbs48OsHfD4fCD5Tj1O4A,2938
-raw_docx-0.7.0.dist-info/licenses/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
-raw_docx-0.7.0.dist-info/METADATA,sha256=aNG1bN6ZnwCWqRv0y2x0-vNhmolaJb8qm04N-gtVvQI,1224
-raw_docx-0.7.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-raw_docx-0.7.0.dist-info/top_level.txt,sha256=Xl3dspPM9DBVj8clfdkHG7N4nNjNXeUmB4HcXAwOe60,9
-raw_docx-0.7.0.dist-info/RECORD,,
+raw_docx-0.8.0.dist-info/licenses/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
+raw_docx-0.8.0.dist-info/METADATA,sha256=jf9pYmWbkI5JKYuucP9mps0Pp9CXgZsywPLHTEAv-L0,1237
+raw_docx-0.8.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+raw_docx-0.8.0.dist-info/top_level.txt,sha256=Xl3dspPM9DBVj8clfdkHG7N4nNjNXeUmB4HcXAwOe60,9
+raw_docx-0.8.0.dist-info/RECORD,,