From ba61808ab806de4818622fc08682b79b8ba0ed7a Mon Sep 17 00:00:00 2001
From: Vik Paruchuri <vik.paruchuri@gmail.com>
Date: Thu, 2 Jan 2025 14:01:54 -0500
Subject: [PATCH] cleanup changes

---
 marker/converters/pdf.py                      |  4 +-
 .../processors/llm/llm_image_description.py   | 65 -------------------
 2 files changed, 1 insertion(+), 68 deletions(-)

diff --git a/marker/converters/pdf.py b/marker/converters/pdf.py
index 23fc9545..bfe9d327 100644
--- a/marker/converters/pdf.py
+++ b/marker/converters/pdf.py
@@ -1,7 +1,4 @@
 import os
-
-from marker.processors.llm.llm_image_description import LLMImageDescriptionProcessor
-
 os.environ["TOKENIZERS_PARALLELISM"] = "false" # disables a tokenizers warning
 
 import inspect
@@ -24,6 +21,7 @@
 from marker.processors.llm.llm_form import LLMFormProcessor
 from marker.processors.llm.llm_table import LLMTableProcessor
 from marker.processors.llm.llm_text import LLMTextProcessor
+from marker.processors.llm.llm_image_description import LLMImageDescriptionProcessor
 from marker.processors.ignoretext import IgnoreTextProcessor
 from marker.processors.line_numbers import LineNumbersProcessor
 from marker.processors.list import ListProcessor
diff --git a/marker/processors/llm/llm_image_description.py b/marker/processors/llm/llm_image_description.py
index 4ff314cb..837e5fcf 100644
--- a/marker/processors/llm/llm_image_description.py
+++ b/marker/processors/llm/llm_image_description.py
@@ -1,17 +1,11 @@
-from tabled.schema import SpanTableCell
-
 from marker.processors.llm import BaseLLMProcessor
-from bs4 import BeautifulSoup
-from typing import List
 
 from google.ai.generativelanguage_v1beta.types import content
-from tabled.formats import html_format
 
 from marker.schema import BlockTypes
 from marker.schema.blocks import Block
 from marker.schema.document import Document
 from marker.schema.groups.page import PageGroup
-from marker.schema.polygon import PolygonBox
 
 
 class LLMImageDescriptionProcessor(BaseLLMProcessor):
@@ -66,62 +60,3 @@ def process_rewriting(self, document: Document, page: PageGroup, block: Block):
             return
 
         block.description = image_description
-
-
-    def parse_html_table(self, html_text: str, block: Block) -> List[SpanTableCell]:
-        soup = BeautifulSoup(html_text, 'html.parser')
-        table = soup.find('table')
-
-        # Initialize grid
-        rows = table.find_all('tr')
-        cells = []
-        max_cols = max(len(row.find_all(['td', 'th'])) for row in rows)
-        if max_cols == 0:
-            return []
-
-        grid = [[True] * max_cols for _ in range(len(rows))]
-
-        for i, row in enumerate(rows):
-            cur_col = 0
-            row_cells = row.find_all(['td', 'th'])
-            for j, cell in enumerate(row_cells):
-                while cur_col < max_cols and not grid[i][cur_col]:
-                    cur_col += 1
-
-                if cur_col >= max_cols:
-                    print("Table parsing warning: too many columns found")
-                    break
-
-                cell_text = cell.text.strip()
-                rowspan = min(int(cell.get('rowspan', 1)), len(rows) - i)
-                colspan = min(int(cell.get('colspan', 1)), max_cols - cur_col)
-                cell_rows = list(range(i, i + rowspan))
-                cell_cols = list(range(cur_col, cur_col + colspan))
-
-                if colspan == 0 or rowspan == 0:
-                    print("Table parsing warning: invalid colspan or rowspan")
-                    continue
-
-                for r in cell_rows:
-                    for c in cell_cols:
-                        grid[r][c] = False
-
-                cell_bbox = [
-                    block.polygon.bbox[0] + cur_col,
-                    block.polygon.bbox[1] + i,
-                    block.polygon.bbox[0] + cur_col + colspan,
-                    block.polygon.bbox[1] + i + rowspan
-                ]
-                cell_polygon = PolygonBox.from_bbox(cell_bbox)
-
-                cell_obj = SpanTableCell(
-                    text=cell_text,
-                    row_ids=cell_rows,
-                    col_ids=cell_cols,
-                    bbox=cell_polygon.bbox
-                )
-                cells.append(cell_obj)
-                cur_col += colspan
-
-
-        return cells