Adrian RatiuThis adds a new check to detect HT in the middle of sentences that should have been a SP, as suggested by Junio in https://public-inbox.org/git/xmqqy0mwsedz.fsf@gitster.g/
The check is a bit complex because we want to detect places where a SP was intended and the naive before/after character check can issue false positives in cases like "a\tb".
The new check is enabled for Documentation/**/*.adoc, where these kinds of mistakes were seen in practice.
Suggested-by: Junio C Hamano <gitster@pobox.com> Signed-off-by: Adrian Ratiu <adrian.ratiu@collabora.com> --- This is based on the latest master branch. Pushed to GitHub: https://github.com/10ne1/git/tree/dev/aratiu/whitespace-new-test-v1 CI run: https://github.com/10ne1/git/actions/runs/20457905508 --- .gitattributes | 2 +- t/t4015-diff-whitespace.sh | 56 ++++++++++++++++++++++++++++++++++++++ ws.c | 32 ++++++++++++++++++++++ ws.h | 1 + 4 files changed, 90 insertions(+), 1 deletion(-)
Show changes to 4 files +90 −1
.gitattributes, t/t4015-diff-whitespace.sh, ws.c, ws.h
diff --git a/.gitattributes b/.gitattributes index 700743c3f5..d3c40a038b 100644 --- a/.gitattributes +++ b/.gitattributes @@ -7,7 +7,7 @@ *.py text eol=lf diff=python *.bat text eol=crlf CODE_OF_CONDUCT.md -whitespace -/Documentation/**/*.adoc text eol=lf whitespace=trail,space,incomplete +/Documentation/**/*.adoc text eol=lf whitespace=trail,space,incomplete,tab-between-non-ws /command-list.txt text eol=lf /GIT-VERSION-GEN text eol=lf /mergetools/* text eol=lf diff --git a/t/t4015-diff-whitespace.sh b/t/t4015-diff-whitespace.sh index 3c8eb02e4f..afe95f5209 100755 --- a/t/t4015-diff-whitespace.sh +++ b/t/t4015-diff-whitespace.sh @@ -2440,4 +2440,60 @@ test_expect_success 'combine --ignore-blank-lines with --function-context 2' ' test_cmp expect actual ' +test_expect_success 'check tab between non-whitespace (tab-between-non-ws: off)' ' + git config core.whitespace "-tab-between-non-ws" && + printf "1234567\tb" >x && + git add x && + git diff --cached --check +' + +test_expect_success 'check tab between non-whitespace at tab stop (tab-between-non-ws: on)' ' + git config core.whitespace "tab-between-non-ws,tabwidth=8" && + printf "1234567\tb" >x && + git add x && + test_must_fail git diff --cached --check +' + +test_expect_success 'check tab between non-whitespace not at tab stop (tab-between-non-ws: on)' ' + git config core.whitespace "tab-between-non-ws,tabwidth=8" && + printf "a\tb" >x && + git add x && + git diff --cached --check +' + +test_expect_success 'check tab between non-whitespace with tabwidth=4 (tab-between-non-ws: on)' ' + git config core.whitespace "tab-between-non-ws,tabwidth=4" && + printf "123\tb" >x && + git add x && + test_must_fail git diff --cached --check +' + +test_expect_success 'check tab between non-whitespace with tabwidth=4 (tab-between-non-ws: on)' ' + git config core.whitespace "tab-between-non-ws,tabwidth=4" && + printf "1234\tb" >x && + git add x && + git diff --cached --check +' + +test_expect_success 'check multiple tabs with one error (tab-between-non-ws: on)' ' + git config core.whitespace "tab-between-non-ws,tabwidth=8" && + printf "a\t1234567\tb" >x && + git add x && + test_must_fail git diff --cached --check +' + +test_expect_success 'check tab at beginning of line (tab-between-non-ws: on)' ' + git config core.whitespace "tab-between-non-ws,tabwidth=8" && + printf "\ta" >x && + git add x && + git diff --cached --check +' + +test_expect_success 'check tab at end of line(tab-between-non-ws: on)' ' + git config core.whitespace "tab-between-non-ws,-trailing-space,tabwidth=8" && + printf "a\t" >x && + git add x && + git diff --cached --check +' + test_done diff --git a/ws.c b/ws.c index 6cc2466c0c..fcd81250ad 100644 --- a/ws.c +++ b/ws.c @@ -26,6 +26,7 @@ static struct whitespace_rule { { "blank-at-eol", WS_BLANK_AT_EOL, 0 }, { "blank-at-eof", WS_BLANK_AT_EOF, 0 }, { "tab-in-indent", WS_TAB_IN_INDENT, 0, 1 }, + { "tab-between-non-ws", WS_TAB_BETWEEN_NON_WS, 0 }, { "incomplete-line", WS_INCOMPLETE_LINE, 0, 0 }, }; @@ -140,6 +141,11 @@ char *whitespace_error_string(unsigned ws) strbuf_addstr(&err, ", "); strbuf_addstr(&err, "tab in indent"); } + if (ws & WS_TAB_BETWEEN_NON_WS) { + if (err.len) + strbuf_addstr(&err, ", "); + strbuf_addstr(&err, "tab between non-whitespace characters"); + } if (ws & WS_INCOMPLETE_LINE) { if (err.len) strbuf_addstr(&err, ", "); @@ -228,6 +234,32 @@ static unsigned ws_check_emit_1(const char *line, int len, unsigned ws_rule, written = i; } + if (ws_rule & WS_TAB_BETWEEN_NON_WS) { + /* + * A tab surrounded by non-whitespace characters is a typo candidate + * (a space might have been intended). This checks for a tab that + * would be expanded to a single space, which is when it appears at + * a column that is one less than a multiple of the tabwidth. + */ + int col = 0; + int tabwidth = ws_tab_width(ws_rule); + + if (!tabwidth) + BUG("a known tabwidth is required by WS_TAB_BETWEEN_NON_WS"); + + for (i = 0; i < len; i++) { + if (line[i] == '\t') { + if (i > 0 && i < len - 1 && + !isspace(line[i - 1]) && !isspace(line[i + 1]) && + (col % tabwidth) == (tabwidth - 1)) + result |= WS_TAB_BETWEEN_NON_WS; + col += tabwidth - (col % tabwidth); + } else { + col++; + } + } + } + if (stream) { /* * Now the rest of the line starts at "written". diff --git a/ws.h b/ws.h index 06d5cb73f8..35475fd320 100644 --- a/ws.h +++ b/ws.h @@ -16,6 +16,7 @@ struct strbuf; #define WS_BLANK_AT_EOF (1<<10) #define WS_TAB_IN_INDENT (1<<11) #define WS_INCOMPLETE_LINE (1<<12) +#define WS_TAB_BETWEEN_NON_WS (1<<13) #define WS_TRAILING_SPACE (WS_BLANK_AT_EOL|WS_BLANK_AT_EOF) #define WS_DEFAULT_RULE (WS_TRAILING_SPACE|WS_SPACE_BEFORE_TAB|8)
-- 2.51.2
