swung0x48/MobileGL
1
0
Fork 0
mirror of https://github.com/MobileGL-Dev/MobileGL synced 2026-11-07 01:53:24 +09:00
Code Issues Packages Projects Releases Wiki Activity

[tools] (P7): the audit's strip reads a prefixed character literal as a character, not as a digit separator

Browse Source 
- L'"', u'"', U'"' and u8'"': the `'` after an identifier character was taken for a C++14
  digit separator, the `"` inside it opened a phantom string, and the rest of the line was
  blanked - a site on that line vanished and its row read as NO SITE (fail-closed: a false red)
- CHAR_PREFIX accepts a u8/u/U/L prefix before `'` the way RAW_PREFIX does before `"`, with
  a non-identifier character (or the start of the text) in front of it, so a real separator
  (0xAB'CD, 1'000) is untouched
- self-test fixture with L'"' and u8'"' ahead of two AT sites on their own lines: rc 0; it
  was rc 1 on the previous audit. The tree has no prefixed character literal today (53 / 53 / 0)
This commit is contained in:
swung0x48
2026-09-22 21:28:01 -04:00
parent 9d5f5012c7
commit 576fc09a31
1 changed files with 15 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
scripts/ci/wire_declines_audit.py
+15 -2
View File
@@ -54,13 +54,18 @@ COUNT_SITE = re.compile(r"WireDeclineTally::Count\(\s*WireDeclineSite::([A-Za-z]
# every time but logged only sometimes is the unlogged site this check exists to refuse.
LOGGED = re.compile(r"^\s*MGLOG_[WE](_ONCE)?\s*\(")
RAW_PREFIX = re.compile(r"(?:^|[^A-Za-z0-9_])(?:u8|u|U|L)?R$")
# The same shape for a character literal: `L'"'` is a wide char, not the identifier `L` followed
# by a digit separator - and read the other way the `"` inside it opens a phantom string that
# blanks the rest of the line, sites included.
CHAR_PREFIX = re.compile(r"(?:^|[^A-Za-z0-9_])(?:u8|u|U|L)$")
def strip_code(text: str) -> str:
"""Blank out //, /* */ comments and string / character literals, keeping every newline.
What remains lines up with the source line for line, so a match's index is a real line
number. Raw strings R"d(...)d" and C++14 digit separators (1'000) are handled."""
number. Raw strings R"d(...)d", prefixed character literals (L'x', u8'x') and C++14 digit
separators (1'000) are handled."""
out = list(text)
n = len(text)
i = 0
@@ -98,7 +103,8 @@ def strip_code(text: str) -> str:
j = n if close < 0 else close + len(delim) + 2
blank(i, j)
i = j
elif c == '"' or (c == "'" and not (i > 0 and (text[i - 1].isalnum() or text[i - 1] == "_"))):
elif c == '"' or (c == "'" and (CHAR_PREFIX.search(text[max(0, i - 3):i])
or not (i > 0 and (text[i - 1].isalnum() or text[i - 1] == "_")))):
j = i + 1
while j < n and text[j] != c and text[j] != "\n":
j += 2 if text[j] == "\\" else 1
@@ -251,6 +257,13 @@ SELF_TEST_FIXTURES = (
" g ? MGLOG_E(\"or only then\") : (void)0;\n"
" WireDeclineTally::Count(WireDeclineSite::GhostRow);\n"
"}\n", 1, NO_LOG),
("prefixed char literals (L'\"', u8'\"') before a site on the same line",
"MGL_WIRE_DECLINE(WideQuote)\nMGL_WIRE_DECLINE(Utf8Quote)\n",
"bool F(wchar_t w, char8_t c) {\n"
" if (w == L'\"') MGL_WIRE_DECLINE_AT(WideQuote, \"a wide double quote\");\n"
" if (c == u8'\"') MGL_WIRE_DECLINE_AT(Utf8Quote, \"a utf-8 double quote\");\n"
" return true;\n"
"}\n", 0, "0 unlogged, 0 unknown"),
("good sites (AT form, bare Count under its own W/E, def row with trailing comment)",
"MGL_WIRE_DECLINE(GoodAt) // the macro form\nMGL_WIRE_DECLINE(GoodBare)\n",
"bool F(int x) {\n"