Monkey patched openpyxl for ranges #33

tests/test_merge_cells.py

@@ -0,0 +1,43 @@
+import pytest
+from openpyxl.utils import range_boundaries
+from xlsx2html import xlsx2html
+from xlsx2html.parser.parser import XLSXParser
+
+
+def test_monkey_patched():
+    assert range_boundaries._monkey
+
+
+@pytest.mark.parametrize(
+    "range,expect_result",
+    [
+        ["A:A", (1, 1, 1, 1048576)],
+        ["2:2", (1, 2, 18278, 2)],
+        ["B2:B", (2, 2, 2, 1048576)],
+        ["D2:2", (4, 2, 18278, 2)],
+    ],
+)
+def test_range_boundaries(range, expect_result):
+    result = range_boundaries(range)
+    assert result == expect_result
+
+
+@pytest.mark.skip("TODO optimize large merges")
+def test_parse_merge_cells(fixture_file):
+    p = XLSXParser(filepath=fixture_file("merge_cells.xlsx"))
+    result = p.get_sheet()
+    assert result
+    assert len(result.cols) == 4
+    assert len(result.rows) == 11
+
+
+@pytest.mark.skip("TODO optimize large merges")
+@pytest.mark.webtest()
+def test_merge_cells(temp_file, browser, screenshot_regression, fixture_file):
+    browser.driver.set_window_size(1280, 1024)
+    out_file = temp_file()
+
+    xlsx2html(fixture_file("merge_cells.xlsx"), out_file, locale="en")
+
+    browser.visit("file://" + out_file)
+    screenshot_regression()

xlsx2html/__init__.py

@@ -2,6 +2,7 @@
 import warnings
 from typing import TextIO
 
+from . import monkey_patch  # noqa
 from .core import xlsx2html, XLSX2HTMLConverter
 
 __all__ = ["xls2html", "xlsx2html", "XLSX2HTMLConverter"]

xlsx2html/monkey_patch.py

@@ -0,0 +1,74 @@
+# type: ignore
+import functools
+
+import openpyxl
+from openpyxl import utils
+from openpyxl.utils import cell
+from openpyxl.worksheet.cell_range import CellRange
+
+old_range_boundaries = cell.range_boundaries
+
+MAX_COL_INDEX = 18278
+MAX_ROW_INDEX = 1048576
+
+
+@functools.wraps(old_range_boundaries)
+def new_range_boundaries(range_string):
+    """
+    patch for handle string like
+    A:A - all column
+    2:2 - all row
+    A2:A - from row 2 to end rows
+    B3:3 - from column B to end columns
+    """
+    from openpyxl.utils.cell import ABSOLUTE_RE
+
+    m = ABSOLUTE_RE.match(range_string)
+    if m:
+        min_col, min_row, sep, max_col, max_row = m.groups()
+        if sep:
+            if not max_col:
+                max_col = utils.get_column_letter(MAX_COL_INDEX)
+            if not max_row:
+                max_row = str(MAX_ROW_INDEX)
+        range_string = "".join(
+            [min_col or utils.get_column_letter(1), min_row or "1", ":", max_col, max_row]
+        )
+
+    min_col, min_row, max_col, max_row = old_range_boundaries(range_string)
+    return min_col or 1, min_row or 1, max_col or MAX_COL_INDEX, max_row or MAX_ROW_INDEX
+
+
+new_range_boundaries._monkey = True
+cell.range_boundaries = new_range_boundaries
+utils.range_boundaries = new_range_boundaries
+openpyxl.utils = utils
+
+
+def CellRange__init__(
+    self, range_string=None, min_col=None, min_row=None, max_col=None, max_row=None, title=None
+):
+    if range_string is not None:
+        if "!" in range_string:
+            from openpyxl.utils import range_to_tuple
+
+            title, (min_col, min_row, max_col, max_row) = range_to_tuple(range_string)
+        else:
+            # FIX
+            min_col, min_row, max_col, max_row = new_range_boundaries(range_string)
+
+    self.min_col = min_col
+    self.min_row = min_row
+    self.max_col = max_col
+    self.max_row = max_row
+    self.title = title
+
+    if min_col > max_col:
+        fmt = "{max_col} must be greater than {min_col}"
+        raise ValueError(fmt.format(min_col=min_col, max_col=max_col))
+    if min_row > max_row:
+        fmt = "{max_row} must be greater than {min_row}"
+        raise ValueError(fmt.format(min_row=min_row, max_row=max_row))
+
+
+CellRange.__init__ = CellRange__init__

xlsx2html/parser/parser.py

@@ -8,7 +8,6 @@
 from openpyxl.drawing.image import Image
 from openpyxl.utils import rows_from_range, column_index_from_string
 from openpyxl.worksheet.worksheet import Worksheet
-
 from xlsx2html.compat import OPENPYXL_24
 from xlsx2html.parser.cell import CellInfo, Borders
 from xlsx2html.parser.image import ImageInfo
@@ -64,6 +63,7 @@ def get_sheet(self, sheet: SheetNameType = None) -> ParserResult:
             excluded_cells = set(ws.merged_cells)
         else:
             merged_cell_ranges = [cell_range.coord for cell_range in ws.merged_cells.ranges]
+            # TODO Optimize for large merge
             excluded_cells = set(
                 [
                     cell
@@ -72,7 +72,7 @@ def get_sheet(self, sheet: SheetNameType = None) -> ParserResult:
                     for cell in rows
                 ]
             )
-
+        # TODO optimize for large merge
         for cell_range in merged_cell_ranges:
             cell_range_list = list(ws[cell_range])
             m_cell = cell_range_list[0][0]