markdown escaping: Fix injection of escapes

c437630 ("Fix markdown character escaping bug (issue #1236)")

fixed the escaping of multiple markdown markers, but it dropped dividing
by two the number of escaped characters being injected:

-                        txt_frag[: -((num_escape_chars + 1) // 2)]

+                    for _ in range(escape_run - 1):

This restores dividing by two the number of escapes, and restores the
test results accordingly, making it the behavior closer to
https://spec.commonmark.org/dingus/

Fixes: #1215

Author: sthibaul

CHANGELOG.md

@@ -26,6 +26,7 @@ This can also be enabled programmatically with `warnings.simplefilter('default',
 * dependency extras for camelot-py and endesive on pyproject.toml - _cf._ [issue #1792](https://github.com/py-pdf/fpdf2/issues/1792)
 * preserve link annotations during dry-run of pdf.multi_cell - _cf._ [issue #1807](https://github.com/py-pdf/fpdf2/issues/1807)
 * preserve two consecutive markdown links (without space inbetween) - _cf._ [issue #1814](https://github.com/py-pdf/fpdf2/issues/1814)
+* number of surviving escape characters - .cf. [issue #1215](https://github.com/py-pdf/fpdf2/issues/1215)
 ### Changed
 * skip byte-for-byte compressed data comparison when zlib-ng is detected, regardless of OS
 

fpdf/fpdf.py

@@ -4486,7 +4486,7 @@ def frag() -> Fragment:
                     self.MARKDOWN_UNDERLINE_MARKER,
                 )
                 if is_escape_target and escape_run % 2 == 1:
-                    for _ in range(escape_run - 1):
+                    for _ in range(escape_run // 2):
                         txt_frag.append(self.MARKDOWN_ESCAPE_CHARACTER)
                     if current_fallback_font:
                         if txt_frag:
@@ -4495,7 +4495,7 @@ def frag() -> Fragment:
                     escape_next_marker = 2
                     escape_run = 0
                     continue
-                for _ in range(escape_run):
+                for _ in range((escape_run + 1) // 2):
                     txt_frag.append(self.MARKDOWN_ESCAPE_CHARACTER)
                 escape_run = 0
 

test/text/cell_markdown_escaped.pdf

@@ -118,10 +118,39 @@ def test_markdown_unrelated_escape():
     )
     expected = (Fragment("unrelated \\ escape **bold**", GSTATE, k=PDF.k),)
     assert frags == expected
+
     frags = merge_fragments(
         tuple(FPDF()._parse_chars("unrelated \\\\ double escape \\**bold\\**", True))
     )
-    expected = (Fragment("unrelated \\\\ double escape **bold**", GSTATE, k=PDF.k),)
+    expected = (Fragment("unrelated \\ double escape **bold**", GSTATE, k=PDF.k),)
+    assert frags == expected
+
+    frags = merge_fragments(
+        tuple(FPDF()._parse_chars("unrelated \\\\\\ triple escape \\**bold\\**", True))
+    )
+    expected = (Fragment("unrelated \\\\ triple escape **bold**", GSTATE, k=PDF.k),)
+    assert frags == expected
+
+    frags = merge_fragments(
+        tuple(
+            FPDF()._parse_chars(
+                "unrelated \\\\\\\\ quadruple escape \\**bold\\**", True
+            )
+        )
+    )
+    expected = (Fragment("unrelated \\\\ quadruple escape **bold**", GSTATE, k=PDF.k),)
+    assert frags == expected
+
+    frags = merge_fragments(
+        tuple(
+            FPDF()._parse_chars(
+                "unrelated \\\\\\\\\\ quintuple escape \\**bold\\**", True
+            )
+        )
+    )
+    expected = (
+        Fragment("unrelated \\\\\\ quintuple escape **bold**", GSTATE, k=PDF.k),
+    )
     assert frags == expected
 
 
@@ -130,16 +159,48 @@ def test_markdown_parse_multiple_escape():
         tuple(FPDF()._parse_chars("\\\\**bold\\\\** double escaped", True))
     )
     expected = (
-        Fragment("\\\\", GSTATE, k=PDF.k),
-        Fragment("bold\\\\", GSTATE_B, k=PDF.k),
+        Fragment("\\", GSTATE, k=PDF.k),
+        Fragment("bold\\", GSTATE_B, k=PDF.k),
         Fragment(" double escaped", GSTATE, k=PDF.k),
     )
-
     assert frags == expected
+
     frags = merge_fragments(
         tuple(FPDF()._parse_chars("\\\\\\**triple bold\\\\\\** escaped", True))
     )
-    expected = (Fragment("\\\\**triple bold\\\\** escaped", GSTATE, k=PDF.k),)
+    expected = (Fragment("\\**triple bold\\** escaped", GSTATE, k=PDF.k),)
+    assert frags == expected
+
+    frags = merge_fragments(
+        tuple(FPDF()._parse_chars("\\\\\\\\**quadruple bold\\\\\\\\** escaped", True))
+    )
+    expected = (
+        Fragment("\\\\", GSTATE, k=PDF.k),
+        Fragment("quadruple bold\\\\", GSTATE_B, k=PDF.k),
+        Fragment(" escaped", GSTATE, k=PDF.k),
+    )
+    assert frags == expected
+
+    frags = merge_fragments(
+        tuple(
+            FPDF()._parse_chars("\\\\\\\\\\**quintuple bold\\\\\\\\\\** escaped", True)
+        )
+    )
+    expected = (Fragment("\\\\**quintuple bold\\\\** escaped", GSTATE, k=PDF.k),)
+    assert frags == expected
+
+    frags = merge_fragments(
+        tuple(
+            FPDF()._parse_chars(
+                "\\\\\\\\\\\\**sextuple bold\\\\\\\\\\\\** escaped", True
+            )
+        )
+    )
+    expected = (
+        Fragment("\\\\\\", GSTATE, k=PDF.k),
+        Fragment("sextuple bold\\\\\\", GSTATE_B, k=PDF.k),
+        Fragment(" escaped", GSTATE, k=PDF.k),
+    )
     assert frags == expected
 
 
@@ -270,7 +331,7 @@ def test_markdown_parse_escape_non_marker():
 def test_markdown_parse_escape_before_marker_odd_even():
     frags = tuple(FPDF()._parse_chars("\\\\**bold**", True))
     expected = (
-        Fragment("\\\\", GSTATE, k=PDF.k),
+        Fragment("\\", GSTATE, k=PDF.k),
         Fragment("bold", GSTATE_B, k=PDF.k),
     )
     assert frags == expected