doc-page-extractor 0.0.7__tar.gz → 0.0.9__tar.gz

{doc_page_extractor-0.0.7 → doc_page_extractor-0.0.9}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.2
+Metadata-Version: 2.4
 Name: doc-page-extractor
-Version: 0.0.7
+Version: 0.0.9
 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
@@ -19,6 +19,7 @@ Dynamic: author-email
 Dynamic: description
 Dynamic: description-content-type
 Dynamic: home-page
+Dynamic: license-file
 Dynamic: requires-dist
 Dynamic: summary
 

{doc_page_extractor-0.0.7 → doc_page_extractor-0.0.9}/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-0.0.9}/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-0.0.9}/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-0.0.9}/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 proto_texts_len == 0:
+      continue
+
     fragments.append(OCRFragment(
       order=min_order,
       text=" ".join(texts),
@@ -112,11 +115,14 @@ def _split_fragments_into_groups(fragments: list[OCRFragment]) -> Generator[list
     height = y2 - y1
     median = (y1 + y2) / 2.0
 
+    if height == 0:
+      continue
+
     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
 
+      deviation_rate = abs(median - next_mean_median) / next_mean_height
       if deviation_rate > max_deviation_rate:
         yield group
         group = []
@@ -141,7 +147,12 @@ 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-0.0.9/doc_page_extractor/plot.py

@@ -0,0 +1,91 @@
+from typing import Iterable
+from PIL import ImageDraw
+from PIL.ImageFont import load_default, FreeTypeFont
+from PIL.Image import Image
+from .types import Layout, LayoutClass
+from .rectangle import Point
+
+_FRAGMENT_COLOR = (0x49, 0xCF, 0xCB) # Light Green
+_Color = tuple[int, int, int]
+
+def plot(image: Image, layouts: Iterable[Layout]) -> None:
+  layout_font = load_default(size=35)
+  fragment_font = load_default(size=25)
+  draw = ImageDraw.Draw(image, mode="RGBA")
+
+  def _draw_number(position: Point, number: int, font: FreeTypeFont, bold: bool, color: _Color) -> None:
+    nonlocal draw
+    x, y = position
+    text = str(object=number)
+    width = len(text) * font.size
+    offset = round(font.size * 0.15)
+
+    for dx, dy in _generate_delta(bold):
+      draw.text(
+        xy=(x + dx - width - offset, y + dy),
+        text=text,
+        font=font,
+        fill=color,
+      )
+
+  for layout in layouts:
+    draw.polygon(
+      xy=[p for p in layout.rect],
+      outline=_layout_color(layout),
+      width=5,
+    )
+
+  for layout in layouts:
+    for fragment in layout.fragments:
+      draw.polygon(
+        xy=[p for p in fragment.rect],
+        outline=_FRAGMENT_COLOR,
+        width=3,
+      )
+      _draw_number(
+        position=fragment.rect.lt,
+        number=fragment.order + 1,
+        font=fragment_font,
+        bold=False,
+        color=_FRAGMENT_COLOR,
+      )
+
+  for i, layout in enumerate(layouts):
+    _draw_number(
+      position=layout.rect.lt,
+      number=i + 1,
+      font=layout_font,
+      bold=True,
+      color=_layout_color(layout),
+    )
+
+def _generate_delta(bold: bool):
+  if bold:
+    for dx in range(-1, 2):
+      for dy in range(-1, 2):
+        yield dx, dy
+  else:
+    yield 0, 0
+
+def _layout_color(layout: Layout) -> _Color:
+  cls = layout.cls
+  if cls == LayoutClass.TITLE:
+    return (0x0A, 0x12, 0x2C) # Dark
+  elif cls == LayoutClass.PLAIN_TEXT:
+    return (0x3C, 0x67, 0x90) # Blue
+  elif cls == LayoutClass.ABANDON:
+    return (0xC0, 0xBB, 0xA9) # Gray
+  elif cls == LayoutClass.FIGURE:
+    return (0x5B, 0x91, 0x3C) # Dark Green
+  elif cls == LayoutClass.FIGURE_CAPTION:
+    return (0x77, 0xB3, 0x54) # Green
+  elif cls == LayoutClass.TABLE:
+    return (0x44, 0x17, 0x52) # Dark Purple
+  elif cls == LayoutClass.TABLE_CAPTION:
+    return (0x81, 0x75, 0xA0) # Purple
+  elif cls == LayoutClass.TABLE_FOOTNOTE:
+    return (0xEF, 0xB6, 0xC9) # Pink Purple
+  elif cls == LayoutClass.ISOLATE_FORMULA:
+    return (0xFA, 0x38, 0x27) # Red
+  elif cls == LayoutClass.FORMULA_CAPTION:
+    return (0xFF, 0x9D, 0x24) # Orange

{doc_page_extractor-0.0.7 → doc_page_extractor-0.0.9}/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-0.0.9}/doc_page_extractor.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.2
+Metadata-Version: 2.4
 Name: doc-page-extractor
-Version: 0.0.7
+Version: 0.0.9
 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
@@ -19,6 +19,7 @@ Dynamic: author-email
 Dynamic: description
 Dynamic: description-content-type
 Dynamic: home-page
+Dynamic: license-file
 Dynamic: requires-dist
 Dynamic: summary
 

{doc_page_extractor-0.0.7 → doc_page_extractor-0.0.9}/setup.py

@@ -2,7 +2,7 @@ from setuptools import setup, find_packages
 
 setup(
   name="doc-page-extractor",
-  version="0.0.7",
+  version="0.0.9",
   author="Tao Zeyu",
   author_email="i@taozeyu.com",
   url="https://github.com/Moskize91/doc-page-extractor",

doc_page_extractor-0.0.7/doc_page_extractor/plot.py

@@ -1,38 +0,0 @@
-from typing import Iterable
-from PIL import ImageDraw
-from PIL.Image import Image
-from .types import Layout, LayoutClass
-
-_FRAGMENT_COLOR = (0x49, 0xCF, 0xCB) # Light Green
-
-def plot(image: Image, layouts: Iterable[Layout]):
-  draw = ImageDraw.Draw(image, mode="RGBA")
-  for layout in layouts:
-    draw.polygon([p for p in layout.rect], outline=_layout_color(layout), width=5)
-
-  for layout in layouts:
-    for fragments in layout.fragments:
-      draw.polygon([p for p in fragments.rect], outline=_FRAGMENT_COLOR, width=3)
-
-def _layout_color(layout: Layout) -> tuple[int, int, int]:
-  cls = layout.cls
-  if cls == LayoutClass.TITLE:
-    return (0x0A, 0x12, 0x2C) # Dark
-  elif cls == LayoutClass.PLAIN_TEXT:
-    return (0x3C, 0x67, 0x90) # Blue
-  elif cls == LayoutClass.ABANDON:
-    return (0xC0, 0xBB, 0xA9) # Gray
-  elif cls == LayoutClass.FIGURE:
-    return (0x5B, 0x91, 0x3C) # Dark Green
-  elif cls == LayoutClass.FIGURE_CAPTION:
-    return (0x77, 0xB3, 0x54) # Green
-  elif cls == LayoutClass.TABLE:
-    return (0x44, 0x17, 0x52) # Dark Purple
-  elif cls == LayoutClass.TABLE_CAPTION:
-    return (0x81, 0x75, 0xA0) # Purple
-  elif cls == LayoutClass.TABLE_FOOTNOTE:
-    return (0xEF, 0xB6, 0xC9) # Pink Purple
-  elif cls == LayoutClass.ISOLATE_FORMULA:
-    return (0xFA, 0x38, 0x27) # Red
-  elif cls == LayoutClass.FORMULA_CAPTION:
-    return (0xFF, 0x9D, 0x24) # Orange