TLDR-918 added table_type, TableRecognition info into docs; added table_type on web

Author: oksidgy

dedoc/api/web/index.html

@@ -13,6 +13,7 @@
         details > summary {font-style: italic; cursor: pointer; display: list-item;}
         .child.max {padding-left: 5px; flex: 1}
         .parent {display: flex}
+        details { padding-left: 24px;}
     </style>
 </head>
 
@@ -142,15 +143,18 @@ <h4>PDF handling</h4>
                     </label>
                 </p>
 
-                <details><summary>need_pdf_table_analysis</summary>
+                <details><summary>need_pdf_table_analysis, table_type</summary>
                 <br>
                     <p>
                     <label>
                         <input type="hidden" name="need_pdf_table_analysis" value="false">
                         <input type="checkbox" name="need_pdf_table_analysis" value="true" checked> need_pdf_table_analysis</label>
                     </p>
+                    <p>
+                        <label>table_type <input name="table_type" type="text" size="20" value=""></label>
+                    </p>
                 </details>
-
+                <br>
                 <p>
                     <label>pages <input name="pages" type="text" size="8" value=":"></label>
                 </p>

dedoc/readers/pdf_reader/data_classes/tables/scantable.py

@@ -10,6 +10,10 @@
 
 
 class ScanTable(Table):
+    """
+    Utility class for storing recognized tables from document images. The class
+    :class:`~dedoc.readers.pdf_reader.pdf_image_reader.table_recognizer.table_recognizer.TableRecognizer` works with this class.
+    """
     def __init__(self, page_number: int, cells: List[List[CellWithMeta]], bbox: BBox, order: int = -1) -> None:
 
         super().__init__(cells, TableMetadata(page_id=page_number))

dedoc/readers/pdf_reader/data_classes/tables/table_type.py

@@ -1,4 +1,61 @@
 class TableTypeAdditionalOptions:
+    """
+    Setting up the table recognizer. The value of the parameter specifies the type of tables recognized when processed by
+    class :class:`~dedoc.readers.pdf_reader.pdf_image_reader.table_recognizer.table_recognizer.TableRecognizer`.
+
+    * Parameter `table_type=wo_external_bounds` - recognize tables without external bounds;
+
+    Example of a table of type `wo_external_bounds`::
+
+       text   | text | text
+      --------+------+------
+       text   | text | text
+      --------+------+------
+       text   | text | text
+      --------+------+------
+       text   | text | text
+
+
+    * Parameter `table_type=one_cell_table` - if a document contains a bounding box with text, it will be considered a table;
+
+    Example of a page with a table of type `one_cell_table`::
+
+         _________________________
+         Header of document
+         text text text +------+
+         text           | text |  <--- it is a table
+                        +------+
+         ________________________
+
+    * Parameter `table_type=split_last_column` - specified parameter for the merged last column of the table;
+
+    Example of a table of type `split_last_column`::
+
+         +--------+------+-------+
+         | text   | text | text1 |
+         +--------+------+       |
+         | text0  | text | text2 |
+         |        | -----|       |
+         |        | text | text3 |
+         +--------+------+       |
+         | text   | text | text4 |
+         +--------+------+-------+
+                     |
+                 Recognition
+                    |
+                    V
+         +--------+------+-------+
+         | text   | text | text1 |
+         +--------+------+-------|
+         | text0  | text | text2 |
+         |--------+ -----+------ |
+         | text0  | text | text3 |
+         +--------+------+------ |
+         | text   | text | text4 |
+         +--------+------+-------+
+
+    """
+
     def __init__(self) -> None:
         self.table_wo_external_bounds = "wo_external_bounds"
         self.detect_one_cell_table = "one_cell_table"

dedoc/readers/pdf_reader/pdf_image_reader/table_recognizer/table_recognizer.py

@@ -19,7 +19,18 @@
 """-------------------------------------entry class of Table Recognizer Module---------------------------------------"""
 
 
-class TableRecognizer(object):
+class TableRecognizer:
+    """
+    The class recognizes tables from document images. This class is internal to the system. It is called from readers such as .
+
+    * The class recognizes tables with borders from the document image and returns the class
+        (function :meth:`~dedoc.readers.pdf_reader.pdf_image_reader.table_recognizer.table_recognizer.TableRecognizer.recognize_tables_from_image`);
+
+
+    * The class also analyzes recognized single-page tables and combines them into multi-page ones
+        (function :meth:`~dedoc.readers.pdf_reader.pdf_image_reader.table_recognizer.table_recognizer.TableRecognizer.convert_to_multipages_tables`);
+
+    """
 
     def __init__(self, *, config: dict = None) -> None:
         self.logger = config.get("logger", logging.getLogger())
@@ -29,10 +40,20 @@ def __init__(self, *, config: dict = None) -> None:
         self.table_type = TableTypeAdditionalOptions()
 
     def convert_to_multipages_tables(self, all_single_tables: List[ScanTable], lines_with_meta: List[LineWithMeta]) -> List[ScanTable]:
+        """
+        The function analyzes recognized tables from the entire document (all pages) to see if they are multi-page.
+        If single-page tables are part of one multi-page, they are combined into one multi-page table.
+        """
         multipage_tables = self.multipage_tables_extractor.extract_multipage_tables(single_tables=all_single_tables, lines_with_meta=lines_with_meta)
         return multipage_tables
 
     def recognize_tables_from_image(self, image: np.ndarray, page_number: int, language: str, table_type: str = "") -> Tuple[np.ndarray, List[ScanTable]]:
+        """
+        The function recognizes tables with borders from scanned document image.
+        Here, the contour analysis method is used to determine the boundaries of table cells.
+        Then, a set of heuristics is used to detect tables, and finally,
+        the detected table cells are converted to a matrix form (merged cells are detected and separated).
+        """
         self.logger.debug(f"Page {page_number}")
         try:
             cleaned_image, scan_tables = self.__rec_tables_from_img(image, page_num=page_number, language=language, table_type=table_type)

docs/source/modules/data_structures.rst

@@ -76,6 +76,11 @@ Helper classes
 .. autoclass:: dedoc.data_structures.AttachedFile
     :members:
 
+
+.. autoclass:: dedoc.readers.pdf_reader.data_classes.tables.scantable.ScanTable
+    :show-inheritance:
+    :members:
+
 .. _annotations:
 
 Annotations of the text lines

docs/source/modules/manager.rst

@@ -10,3 +10,11 @@ Dedoc pipeline
 .. autoclass:: dedoc.attachments_handler.AttachmentsHandler
     :special-members: __init__
     :members:
+
+.. autoclass:: dedoc.readers.pdf_reader.pdf_image_reader.table_recognizer.table_recognizer.TableRecognizer
+    :show-inheritance:
+    :members:
+
+.. autoclass:: dedoc.readers.pdf_reader.data_classes.tables.table_type.TableTypeAdditionalOptions
+    :show-inheritance:
+    :members:

docs/source/parameters/pdf_handling.rst

@@ -169,6 +169,18 @@ PDF and images handling
         If the document has a textual layer, it is recommended to use :class:`dedoc.readers.PdfTabbyReader`,
         in this case tables will be parsed much easier and faster.
 
+    * - table_type
+      - "", wo_external_bounds, one_cell_table, split_last_column and their combinaton
+      - ""
+      - * :meth:`dedoc.DedocManager.parse`
+        * :meth:`dedoc.readers.PdfAutoReader.read`, :meth:`dedoc.readers.PdfTxtlayerReader.read`, :meth:`dedoc.readers.PdfImageReader.read`
+        * :meth:`dedoc.readers.ReaderComposition.read`
+      - Setting up the table recognition method. The table recognition method is used in :class:`dedoc.readers.PdfImageReader` and
+        :class:`dedoc.readers.PdfTxtlayerReader`. The value of the parameter specifies the type of tables recognized when processed by
+        class :class:`~dedoc.readers.pdf_reader.pdf_image_reader.table_recognizer.table_recognizer.TableRecognizer`. More details about each parameter value
+        are disclosed in the class :class:`dedoc.readers.pdf_reader.data_classes.tables.table_type.TableTypeAdditionalOptions` description.
+        You can use combination of values (for example, `wo_external_bounds+one_cell_table`).
+
     * - need_gost_frame_analysis
       - True, False
       - False