Fix wrapping of colored values

.github/workflows/ci.yml

@@ -54,8 +54,9 @@ jobs:
     runs-on: ubuntu-latest
     steps:
     - uses: actions/checkout@v3
+    - run: python -m pip install --upgrade pip
     - run: pip install --user ruff
-    - run: ruff --format=github .
+    - run: ruff --output-format=github .
 
   pyright:
     runs-on: ubuntu-latest

src/wily/commands/diff.py

@@ -17,7 +17,7 @@
 from wily.commands.build import run_operator
 from wily.config import DEFAULT_PATH
 from wily.config.types import WilyConfig
-from wily.helper import get_maxcolwidth, get_style
+from wily.helper import get_maxcolwidth, get_style, handle_long_word
 from wily.operators import (
     BAD_COLORS,
     GOOD_COLORS,
@@ -28,6 +28,11 @@
 )
 from wily.state import State
 
+# Monkeypatch tabulate to fix wrapping bug (https://github.com/astanin/python-tabulate/issues/307):
+if not hasattr(tabulate._CustomTextWrap, "original_handle_long_word"):  # type: ignore
+    tabulate._CustomTextWrap.original_handle_long_word = tabulate._CustomTextWrap._handle_long_word  # type: ignore
+tabulate._CustomTextWrap._handle_long_word = handle_long_word  # type: ignore
+
 
 def diff(
     config: WilyConfig,

src/wily/commands/report.py

@@ -13,12 +13,17 @@
 
 from wily import MAX_MESSAGE_WIDTH, format_date, format_revision, logger
 from wily.config.types import WilyConfig
-from wily.helper import get_maxcolwidth
+from wily.helper import get_maxcolwidth, handle_long_word
 from wily.helper.custom_enums import ReportFormat
 from wily.lang import _
 from wily.operators import MetricType, resolve_metric_as_tuple
 from wily.state import State
 
+# Monkeypatch tabulate to fix wrapping bug (https://github.com/astanin/python-tabulate/issues/307):
+if not hasattr(tabulate._CustomTextWrap, "original_handle_long_word"):  # type: ignore
+    tabulate._CustomTextWrap.original_handle_long_word = tabulate._CustomTextWrap._handle_long_word  # type: ignore
+tabulate._CustomTextWrap._handle_long_word = handle_long_word  # type: ignore
+
 ANSI_RED = 31
 ANSI_GREEN = 32
 ANSI_YELLOW = 33

src/wily/helper/__init__.py

@@ -5,7 +5,9 @@
 import shutil
 import sys
 from functools import lru_cache
-from typing import Optional, Sized, Union
+from typing import List, Optional, Sized, Union
+
+import tabulate
 
 from wily.defaults import DEFAULT_GRID_STYLE
 
@@ -54,3 +56,60 @@ def generate_cache_path(path: Union[pathlib.Path, str]) -> str:
     cache_path = str(HOME / ".wily" / sha)
     logger.debug("Cache path is %s", cache_path)
     return cache_path
+
+
+strip_ansi = tabulate._strip_ansi  # type: ignore
+ansi_codes = tabulate._ansi_codes  # type: ignore
+
+
+def handle_long_word(
+    self, reversed_chunks: List[str], cur_line: List[str], cur_len: int, width: int
+):
+    """
+    Handle a chunk of text that is too long to fit in any line.
+
+    Fixed version of tabulate._CustomTextWrap._handle_long_word that avoids a
+    wrapping bug (https://github.com/astanin/python-tabulate/issues/307) where
+    ANSI escape codes would be broken up in the middle.
+    """
+    # Figure out when indent is larger than the specified width, and make
+    # sure at least one character is stripped off on every pass
+    if width < 1:
+        space_left = 1
+    else:
+        space_left = width - cur_len
+
+    # If we're allowed to break long words, then do so: put as much
+    # of the next chunk onto the current line as will fit.
+    if self.break_long_words:
+        # Tabulate Custom: Build the string up piece-by-piece in order to
+        # take each character's width into account
+        chunk = reversed_chunks[-1]
+        i = 1
+        # Only count printable characters, so strip_ansi first, index later.
+        while len(strip_ansi(chunk)[:i]) <= space_left:
+            i = i + 1
+        # Consider escape codes when breaking words up
+        total_escape_len = 0
+        last_group = 0
+        if ansi_codes.search(chunk) is not None:
+            for group, _, _, _ in ansi_codes.findall(chunk):
+                escape_len = len(group)
+                if group in chunk[last_group : i + total_escape_len + escape_len - 1]:
+                    total_escape_len += escape_len
+                    found = ansi_codes.search(chunk[last_group:])
+                    last_group += found.end()
+        cur_line.append(chunk[: i + total_escape_len - 1])
+        reversed_chunks[-1] = chunk[i + total_escape_len - 1 :]
+
+    # Otherwise, we have to preserve the long word intact.  Only add
+    # it to the current line if there's nothing already there --
+    # that minimizes how much we violate the width constraint.
+    elif not cur_line:
+        cur_line.append(reversed_chunks.pop())
+
+    # If we're not allowed to break long words, and there's already
+    # text on the current line, do nothing.  Next time through the
+    # main loop of _wrap_chunks(), we'll wind up here again, but
+    # cur_len will be zero, so the next line will be entirely
+    # devoted to the long word that we can't handle right now.

test/unit/test_helper.py

@@ -4,7 +4,7 @@
 import tabulate
 
 from wily.defaults import DEFAULT_GRID_STYLE
-from wily.helper import get_maxcolwidth, get_style
+from wily.helper import get_maxcolwidth, get_style, handle_long_word
 
 SHORT_DATA = [list("abcdefgh"), list("abcdefgh")]
 
@@ -156,3 +156,24 @@ def test_get_style_none():
     with mock.patch("sys.stdout", output):
         style = get_style()
     assert style == "fancy_grid"
+
+
+def test_handle_long_word():
+    data = "This_is_a_\033[31mtest_string_for_testing_TextWrap\033[0m_with_colors"
+    expected = [
+        "This_is_a_\033[31mte\033[0m",
+        "\033[31mst_string_fo\033[0m",
+        "\033[31mr_testing_Te\033[0m",
+        "\033[31mxtWrap\033[0m_with_",
+        "colors",
+    ]
+    if hasattr(tabulate._CustomTextWrap, "original_handle_long_word"):  # type: ignore
+        # We've already monkeypatched _CustomTextWrap, undo it.
+        tabulate._CustomTextWrap._handle_long_word = tabulate._CustomTextWrap.original_handle_long_word  # type: ignore
+    wrapper = tabulate._CustomTextWrap(width=12)  # type: ignore
+    result = wrapper.wrap(data)
+    assert result != expected
+    tabulate._CustomTextWrap._handle_long_word = handle_long_word  # type: ignore
+    wrapper = tabulate._CustomTextWrap(width=12)  # type: ignore
+    result = wrapper.wrap(data)
+    assert result == expected