diff --color-moved-ws: handle blank lines

When using --color-moved-ws=allow-indentation-change allow lines with
the same indentation change to be grouped across blank lines. For now
this only works if the blank lines have been moved as well, not for
blocks that have just had their indentation changed.

This completes the changes to the implementation of
--color-moved=allow-indentation-change. Running

git diff --color-moved=allow-indentation-change v2.18.0 v2.19.0

now takes 5.0s. This is a saving of 41% from 8.5s for the optimized
version of the previous implementation and 66% from the original which
took 14.6s.

Signed-off-by: Phillip Wood <phillip.wood@dunelm.org.uk>
Reviewed-by: Stefan Beller <sbeller@google.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

diff --git a/diff.c b/diff.c
index 941956d8c4b4ea00b86deee3a7b3004570109b87..03ffe467e474cf4ecef31cacb3f81a0ba8160fae 100644 (file)
--- a/diff.c
+++ b/diff.c
@@ -794,9 +794,11 @@ static void moved_block_clear(struct moved_block *b)
        memset(b, 0, sizeof(*b));
 }
 
+#define INDENT_BLANKLINE INT_MIN
+
 static void fill_es_indent_data(struct emitted_diff_symbol *es)
 {
-       unsigned int off = 0;
+       unsigned int off = 0, i;
        int width = 0, tab_width = es->flags & WS_TAB_WIDTH_MASK;
        const char *s = es->line;
        const int len = es->len;
@@ -820,8 +822,18 @@ static void fill_es_indent_data(struct emitted_diff_symbol *es)
                }
        }
 
-       es->indent_off = off;
-       es->indent_width = width;
+       /* check if this line is blank */
+       for (i = off; i < len; i++)
+               if (!isspace(s[i]))
+                   break;
+
+       if (i == len) {
+               es->indent_width = INDENT_BLANKLINE;
+               es->indent_off = len;
+       } else {
+               es->indent_off = off;
+               es->indent_width = width;
+       }
 }
 
 static int compute_ws_delta(const struct emitted_diff_symbol *a,
@@ -836,6 +848,11 @@ static int compute_ws_delta(const struct emitted_diff_symbol *a,
            b_width = b->indent_width;
        int delta;
 
+       if (a_width == INDENT_BLANKLINE && b_width == INDENT_BLANKLINE) {
+               *out = INDENT_BLANKLINE;
+               return 1;
+       }
+
        if (a->s == DIFF_SYMBOL_PLUS)
                delta = a_width - b_width;
        else
@@ -879,6 +896,10 @@ static int cmp_in_block_with_wsd(const struct diff_options *o,
        if (al != bl)
                return 1;
 
+       /* If 'l' and 'cur' are both blank then they match. */
+       if (a_width == INDENT_BLANKLINE && c_width == INDENT_BLANKLINE)
+               return 0;
+
        /*
         * The indent changes of the block are known and stored in pmb->wsd;
         * however we need to check if the indent changes of the current line
@@ -890,6 +911,13 @@ static int cmp_in_block_with_wsd(const struct diff_options *o,
        else
                delta = c_width - a_width;
 
+       /*
+        * If the previous lines of this block were all blank then set its
+        * whitespace delta.
+        */
+       if (pmb->wsd == INDENT_BLANKLINE)
+               pmb->wsd = delta;
+
        return !(delta == pmb->wsd && al - a_off == cl - c_off &&
                 !memcmp(a, b, al) && !
                 memcmp(a + a_off, c + c_off, al - a_off));

diff --git a/t/t4015-diff-whitespace.sh b/t/t4015-diff-whitespace.sh
index e023839ba66649426f978d02206bcbe4fb3be267..9d6f88b07fe1d24081758827b2d2025a05ade9a2 100755 (executable)
--- a/t/t4015-diff-whitespace.sh
+++ b/t/t4015-diff-whitespace.sh
@@ -1901,10 +1901,20 @@ test_expect_success 'compare whitespace delta incompatible with other space opti
        test_i18ngrep allow-indentation-change err
 '
 
+EMPTY=''
 test_expect_success 'compare mixed whitespace delta across moved blocks' '
 
        git reset --hard &&
        tr Q_ "\t " <<-EOF >text.txt &&
+       ${EMPTY}
+       ____too short without
+       ${EMPTY}
+       ___being grouped across blank line
+       ${EMPTY}
+       context
+       lines
+       to
+       anchor
        ____Indented text to
        _Q____be further indented by four spaces across
        ____Qseveral lines
@@ -1918,9 +1928,18 @@ test_expect_success 'compare mixed whitespace delta across moved blocks' '
        git commit -m "add text.txt" &&
 
        tr Q_ "\t " <<-EOF >text.txt &&
+       context
+       lines
+       to
+       anchor
        QIndented text to
        QQbe further indented by four spaces across
        Q____several lines
+       ${EMPTY}
+       QQtoo short without
+       ${EMPTY}
+       Q_______being grouped across blank line
+       ${EMPTY}
        Q_QThese two lines have had their
        indentation reduced by four spaces
        QQdifferent indentation change
@@ -1937,7 +1956,16 @@ test_expect_success 'compare mixed whitespace delta across moved blocks' '
        <BOLD>diff --git a/text.txt b/text.txt<RESET>
        <BOLD>--- a/text.txt<RESET>
        <BOLD>+++ b/text.txt<RESET>
-       <CYAN>@@ -1,7 +1,7 @@<RESET>
+       <CYAN>@@ -1,16 +1,16 @@<RESET>
+       <BOLD;MAGENTA>-<RESET>
+       <BOLD;MAGENTA>-<RESET><BOLD;MAGENTA>    too short without<RESET>
+       <BOLD;MAGENTA>-<RESET>
+       <BOLD;MAGENTA>-<RESET><BOLD;MAGENTA>   being grouped across blank line<RESET>
+       <BOLD;MAGENTA>-<RESET>
+        <RESET>context<RESET>
+        <RESET>lines<RESET>
+        <RESET>to<RESET>
+        <RESET>anchor<RESET>
        <BOLD;MAGENTA>-<RESET><BOLD;MAGENTA>    Indented text to<RESET>
        <BOLD;MAGENTA>-<RESET><BRED> <RESET>    <BOLD;MAGENTA>    be further indented by four spaces across<RESET>
        <BOLD;MAGENTA>-<RESET><BRED>    <RESET> <BOLD;MAGENTA>several lines<RESET>
@@ -1948,9 +1976,14 @@ test_expect_success 'compare mixed whitespace delta across moved blocks' '
        <BOLD;CYAN>+<RESET>     <BOLD;CYAN>Indented text to<RESET>
        <BOLD;CYAN>+<RESET>             <BOLD;CYAN>be further indented by four spaces across<RESET>
        <BOLD;CYAN>+<RESET>     <BOLD;CYAN>    several lines<RESET>
-       <BOLD;YELLOW>+<RESET>   <BRED> <RESET>  <BOLD;YELLOW>These two lines have had their<RESET>
-       <BOLD;YELLOW>+<RESET><BOLD;YELLOW>indentation reduced by four spaces<RESET>
-       <BOLD;CYAN>+<RESET>             <BOLD;CYAN>different indentation change<RESET>
+       <BOLD;YELLOW>+<RESET>
+       <BOLD;YELLOW>+<RESET>           <BOLD;YELLOW>too short without<RESET>
+       <BOLD;YELLOW>+<RESET>
+       <BOLD;YELLOW>+<RESET>   <BOLD;YELLOW>       being grouped across blank line<RESET>
+       <BOLD;YELLOW>+<RESET>
+       <BOLD;CYAN>+<RESET>     <BRED> <RESET>  <BOLD;CYAN>These two lines have had their<RESET>
+       <BOLD;CYAN>+<RESET><BOLD;CYAN>indentation reduced by four spaces<RESET>
+       <BOLD;YELLOW>+<RESET>           <BOLD;YELLOW>different indentation change<RESET>
        <GREEN>+<RESET><BRED>  <RESET>  <GREEN>too short<RESET>
        EOF