parse page layout recursively

Author: dothinking

README.md

@@ -14,11 +14,11 @@
     - [x] text in horizontal/vertical direction: from left to right, from bottom to top
     - [x] font style, e.g. font name, size, weight, italic and color
     - [x] text format, e.g. highlight, underline, strike-through
-    - [x] text alignment, e.g. left/right/center/justify    
+    - [x] text alignment, e.g. left/right/center/justify
+    - [x] external hyper link
     - [x] paragraph layout: horizontal alignment and vertical spacing
     - [ ] list style
-    - [ ] href link
-
+    
 - [x] Parse and re-create image
 	- [x] in-line image
     - [x] image in Gray/RGB/CMYK mode
@@ -30,7 +30,8 @@
     - [x] shading style, i.e. background color
     - [x] merged cells
     - [x] vertical direction cell
-    - [x] table with partly hidden borders    
+    - [x] table with partly hidden borders
+    - [x] nested tables
 
 - [x] Parsing pages with multi-processing
 

pdf2docx/common/Block.py

@@ -167,15 +167,6 @@ def is_flow_layout(self, *args):
         return True
 
 
-    def parse_text_format(self, *args, **kwargs):
-        """Parse text format.
-
-        Raises:
-            NotImplementedError
-        """
-        raise NotImplementedError
-
-
     def make_docx(self, *args, **kwargs):
         """Create associated docx element.
 

pdf2docx/common/Collection.py

@@ -10,9 +10,9 @@
 
 class BaseCollection:
     '''Base collection of specific instances.'''
-    def __init__(self, instances:list=[]):
+    def __init__(self, instances:list=None):
         '''Init collection from a list of Element instances.'''
-        self._instances = instances if instances else [] # type: list[Element]
+        self._instances = instances or [] # type: list[Element]
 
     def __getitem__(self, idx):
         try:
@@ -119,7 +119,7 @@ def group_by_connectivity(self, dx:float, dy:float):
 
 class Collection(BaseCollection, IText):
     '''Collection of specific instances.'''
-    def __init__(self, instances:list=[], parent=None):
+    def __init__(self, instances:list=None, parent=None):
         '''Init collection from a list of Element instances.'''
         self._parent = parent # type: Element
         super().__init__(instances)
@@ -250,19 +250,24 @@ def contained_in_bbox(self, bbox):
         return self.__class__(instances)
 
 
-    def split_with_intersection(self, bbox):
+    def split_with_intersection(self, bbox:fitz.Rect, threshold:float=0.0):
         """Split instances into two groups: one intersects with ``bbox``, the other not.
 
         Args:
             bbox (fitz.Rect): target rect box.
+            threshold (float): It's intersected when the overlap rate exceeds this threshold. Defaults to 0.
 
         Returns:
             tuple: two group in original class type.
         """
-        intersection, no_intersection = [], []
+        intersections, no_intersections = [], []
         for instance in self._instances:
-            if bbox.intersects(instance.bbox):
-                intersection.append(instance)
+            # A contains B => A & B = B
+            intersection = instance.bbox & bbox
+            factor = round(intersection.getArea()/instance.bbox.getArea(), 2)
+
+            if factor >= threshold:
+                intersections.append(instance)
             else:
-                no_intersection.append(instance)
-        return self.__class__(intersection), self.__class__(no_intersection)
+                no_intersections.append(instance)
+        return self.__class__(intersections), self.__class__(no_intersections)

pdf2docx/common/share.py

@@ -198,7 +198,7 @@ def new_page(doc, width:float, height:float, title:str):
     return page
 
 
-def debug_plot(title:str):
+def debug_plot(title:str, show=True):
     '''Plot the returned objects of inner function.
     
     Args:
@@ -215,11 +215,11 @@ def inner(*args, **kwargs):
             doc = page.settings.get('debug_doc', None)
             filename = page.settings.get('debug_filename', None)
 
-            if objects and debug and doc is not None:                
+            if show and objects and debug and doc is not None:                
                 # create a new page
-                page = new_page(doc, page.width, page.height, title)
+                debug_page = new_page(doc, page.width, page.height, title)
                 # plot objects, e.g. text blocks, shapes, tables...
-                objects.plot(page)
+                objects.plot(debug_page)
                 doc.save(filename)
 
             return objects