From 344c404932fe03a63c5da825a4ee3cc0cfa1fab2 Mon Sep 17 00:00:00 2001
From: Li Luo <379433439@qq.com>
Date: Wed, 20 Dec 2023 19:40:25 -0500
Subject: [PATCH] feat(page_element): Parse page numbers and separators (PR#59)

---
 .../processing_steps/title_classifier.py      | 12 +++++--
 sec_parser/semantic_elements/page_element.py  | 32 +++++++++++++++++++
 2 files changed, 42 insertions(+), 2 deletions(-)
 create mode 100644 sec_parser/semantic_elements/page_element.py

diff --git a/sec_parser/processing_steps/title_classifier.py b/sec_parser/processing_steps/title_classifier.py
index 7e3b0cc..927a2ec 100644
--- a/sec_parser/processing_steps/title_classifier.py
+++ b/sec_parser/processing_steps/title_classifier.py
@@ -11,6 +11,7 @@
     TextStyle,
 )
 from sec_parser.semantic_elements.title_element import TitleElement
+from sec_parser.semantic_elements.page_element import PageElement
 
 if TYPE_CHECKING:  # pragma: no cover
     from sec_parser.semantic_elements.abstract_semantic_element import (
@@ -59,11 +60,18 @@ def _process_element(
         """Process each element and convert to TitleElement if necessary."""
         if not isinstance(element, HighlightedTextElement):
             return element
-
+       
         # Ensure the style is tracked
         self._add_unique_style(element.style)
 
-        level = self._unique_styles_by_order.index(element.style)
+        level = self._unique_styles_by_order.index(element.style) 
+
+        if PageElement.is_page(source = element):
+            return PageElement.create_from_element(
+                element,
+                log_origin=self.__class__.__name__,
+            )
+        
         return TitleElement.create_from_element(
             element,
             level=level,
diff --git a/sec_parser/semantic_elements/page_element.py b/sec_parser/semantic_elements/page_element.py
new file mode 100644
index 0000000..2b8084b
--- /dev/null
+++ b/sec_parser/semantic_elements/page_element.py
@@ -0,0 +1,32 @@
+from __future__ import annotations
+
+from sec_parser.semantic_elements import IrrelevantElement
+from sec_parser.semantic_elements.abstract_semantic_element import AbstractSemanticElement
+from sec_parser.processing_engine.processing_log import LogItemOrigin, ProcessingLog
+
+
+class PageElement(IrrelevantElement):
+    """
+    The PageElement class represents the page content of a paragraph or other content object.
+    It relates to an irrelevant element, storing page numbers and context for the document.
+    """
+
+    PageNum = 0
+    
+    def is_page(source: AbstractSemanticElement):
+        try:
+            if source.text.__contains__('|'):
+                pageNum = source.text.replace(" ","").split('|')[-1]
+            else:
+                pageNum = int(source.text.strip())
+        except ValueError:
+            return False
+        
+        if PageElement.PageNum == 0:
+            PageElement.PageNum = int(pageNum)
+            
+        if int(pageNum) == PageElement.PageNum:
+            PageElement.PageNum = PageElement.PageNum + 1
+            return True
+        
+        return False