doc-page-extractor 0.0.7__tar.gz → 0.0.8__tar.gz

{doc_page_extractor-0.0.7 → doc_page_extractor-0.0.8}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: doc-page-extractor
-Version: 0.0.7
+Version: 0.0.8
 Summary: doc page extractor can identify text and format in images and return structured data.
 Home-page: https://github.com/Moskize91/doc-page-extractor
 Author: Tao Zeyu

{doc_page_extractor-0.0.7 → doc_page_extractor-0.0.8}/doc_page_extractor/clipper.py

@@ -73,6 +73,9 @@ def _size_and_wrapper(rect: Rectangle):
     else:
       widths.append(distance)
 
+  if len(widths) == 0 and len(heights) == 0:
+    return 0.0, 0.0, 0.0, 0.0
+
   width: float = sum(widths) / len(widths)
   height: float = sum(heights) / len(heights)
   max_width: float = width

{doc_page_extractor-0.0.7 → doc_page_extractor-0.0.8}/doc_page_extractor/extractor.py

@@ -137,6 +137,10 @@ class DocExtractor:
   def _find_matched_layout(self, fragment: OCRFragment, layouts: list[Layout]) -> Layout | None:
     fragment_area = fragment.rect.area
     primary_layouts: list[(Layout, float)] = []
+
+    if fragment_area == 0.0:
+      return None
+
     for layout in layouts:
       area = intersection_area(fragment.rect, layout.rect)
       if area / fragment_area > 0.85:
@@ -169,6 +173,9 @@ class DocExtractor:
       fragment.order = i
 
   def _order_fragments_by_ai(self, width: int, height: int, layouts: list[Layout]):
+    if width == 0 or height == 0:
+      return
+
     layout_model = self._get_layout()
     boxes: list[list[int]] = []
     steps: float = 1000.0 # max value of layoutreader
@@ -268,6 +275,9 @@ class DocExtractor:
     width = right - left
     height = bottom - top
 
+    if width == 0 or height == 0:
+      return
+
     for _left, _top, _right, _bottom in boxes:
       yield (
         (_left - left) / width,

{doc_page_extractor-0.0.7 → doc_page_extractor-0.0.8}/doc_page_extractor/ocr.py

@@ -63,16 +63,21 @@ class OCR:
       text, rank = res
       if is_space_text(text):
         continue
+
+      rect = Rectangle(
+        lt=(box[0][0], box[0][1]),
+        rt=(box[1][0], box[1][1]),
+        rb=(box[2][0], box[2][1]),
+        lb=(box[3][0], box[3][1]),
+      )
+      if rect.area == 0.0:
+        continue
+
       yield OCRFragment(
         order=index,
         text=text,
         rank=rank,
-        rect=Rectangle(
-          lt=(box[0][0], box[0][1]),
-          rt=(box[1][0], box[1][1]),
-          rb=(box[2][0], box[2][1]),
-          lb=(box[3][0], box[3][1]),
-        ),
+        rect=rect,
       )
       index += 1
 

{doc_page_extractor-0.0.7 → doc_page_extractor-0.0.8}/doc_page_extractor/overlap.py

@@ -88,6 +88,9 @@ def regroup_lines(origin_fragments: list[OCRFragment]) -> list[OCRFragment]:
         x2 = max(x2, x)
         y2 = max(y2, y)
 
+    if len(proto_texts_len) == 0:
+      continue
+
     fragments.append(OCRFragment(
       order=min_order,
       text=" ".join(texts),
@@ -115,13 +118,14 @@ def _split_fragments_into_groups(fragments: list[OCRFragment]) -> Generator[list
     if len(group) > 0:
       next_mean_median = (sum_median + median) / (len(group) + 1)
       next_mean_height = (sum_height + height) / (len(group) + 1)
-      deviation_rate = abs(median - next_mean_median) / next_mean_height
 
-      if deviation_rate > max_deviation_rate:
-        yield group
-        group = []
-        sum_height = 0.0
-        sum_median = 0.0
+      if next_mean_height > 0:
+        deviation_rate = abs(median - next_mean_median) / next_mean_height
+        if deviation_rate > max_deviation_rate:
+          yield group
+          group = []
+          sum_height = 0.0
+          sum_median = 0.0
 
     group.append(fragment)
     sum_height += height
@@ -141,7 +145,12 @@ def overlap_rate(polygon1: Polygon, polygon2: Polygon) -> float:
   else:
     overlay_width, overlay_height = _polygon_size(intersection)
     polygon2_width, polygon2_height = _polygon_size(polygon2)
-    return (overlay_width / polygon2_width + overlay_height / polygon2_height) / 2.0
+    if polygon2_width == 0.0 or polygon2_height == 0.0:
+      return 0.0
+    return (
+      overlay_width / polygon2_width +
+      overlay_height / polygon2_height
+    ) / 2.0
 
 def _polygon_size(polygon: Polygon) -> tuple[float, float]:
   x1: float = float("inf")

{doc_page_extractor-0.0.7 → doc_page_extractor-0.0.8}/doc_page_extractor/rotation.py

@@ -129,7 +129,9 @@ def _find_median(rotations: list[float]):
     mid2 = rotations[n // 2]
     return (mid1 + mid2) / 2
 
-def _find_mean(rotations: list[float]):
+def _find_mean(rotations: list[float]) -> float:
+  if len(rotations) == 0:
+    return 0.0
   return sum(rotations) / len(rotations)
 
 # rotation is in [0, pi)

{doc_page_extractor-0.0.7 → doc_page_extractor-0.0.8}/doc_page_extractor.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: doc-page-extractor
-Version: 0.0.7
+Version: 0.0.8
 Summary: doc page extractor can identify text and format in images and return structured data.
 Home-page: https://github.com/Moskize91/doc-page-extractor
 Author: Tao Zeyu

{doc_page_extractor-0.0.7 → doc_page_extractor-0.0.8}/setup.py

@@ -2,7 +2,7 @@ from setuptools import setup, find_packages
 
 setup(
   name="doc-page-extractor",
-  version="0.0.7",
+  version="0.0.8",
   author="Tao Zeyu",
   author_email="i@taozeyu.com",
   url="https://github.com/Moskize91/doc-page-extractor",