Merge branch 'js/diff-color-words'

* js/diff-color-words:
  Change the spelling of "wordregex".
  color-words: Support diff.wordregex config option
  color-words: make regex configurable via attributes
  color-words: expand docs with precise semantics
  color-words: enable REG_NEWLINE to help user
  color-words: take an optional regular expression describing words
  color-words: change algorithm to allow for 0-character word boundaries
  color-words: refactor word splitting and use ALLOC_GROW()
  Add color_fwrite_lines(), a function coloring each line individually

Documentation/config.txt

@@ -639,6 +639,12 @@ diff.suppressBlankEmpty::
 	A boolean to inhibit the standard behavior of printing a space
 	before each empty output line. Defaults to false.
 
+diff.wordRegex::
+	A POSIX Extended Regular Expression used to determine what is a "word"
+	when performing word-by-word difference calculations.  Character
+	sequences that match the regular expression are "words", all other
+	characters are *ignorable* whitespace.
+
 fetch.unpackLimit::
 	If the number of objects fetched over the git native
 	transfer is below this

Documentation/diff-options.txt

@@ -94,8 +94,22 @@ endif::git-format-patch[]
 	Turn off colored diff, even when the configuration file
 	gives the default to color output.
 
---color-words::
+--color-words[=<regex>]::
-	Show colored word diff, i.e. color words which have changed.
+	Show colored word diff, i.e., color words which have changed.
+	By default, words are separated by whitespace.
++
+When a <regex> is specified, every non-overlapping match of the
+<regex> is considered a word.  Anything between these matches is
+considered whitespace and ignored(!) for the purposes of finding
+differences.  You may want to append `|[^[:space:]]` to your regular
+expression to make sure that it matches all non-whitespace characters.
+A match that contains a newline is silently truncated(!) at the
+newline.
++
+The regex can also be set via a diff driver or configuration option, see
+linkgit:gitattributes[1] or linkgit:git-config[1].  Giving it explicitly
+overrides any diff driver or configuration setting.  Diff drivers
+override configuration settings.
 
 --no-renames::
 	Turn off rename detection, even when the configuration

Documentation/gitattributes.txt

@@ -317,6 +317,8 @@ patterns are available:
 
 - `bibtex` suitable for files with BibTeX coded references.
 
+- `cpp` suitable for source code in the C and C++ languages.
+
 - `html` suitable for HTML/XHTML documents.
 
 - `java` suitable for source code in the Java language.
@@ -334,6 +336,25 @@ patterns are available:
 - `tex` suitable for source code for LaTeX documents.
 
 
+Customizing word diff
+^^^^^^^^^^^^^^^^^^^^^
+
+You can customize the rules that `git diff --color-words` uses to
+split words in a line, by specifying an appropriate regular expression
+in the "diff.*.wordRegex" configuration variable.  For example, in TeX
+a backslash followed by a sequence of letters forms a command, but
+several such commands can be run together without intervening
+whitespace.  To separate them, use a regular expression such as
+
+------------------------
+[diff "tex"]
+	wordRegex = "\\\\[a-zA-Z]+|[{}]|\\\\.|[^\\{}[:space:]]+"
+------------------------
+
+A built-in pattern is provided for all languages listed in the
+previous section.
+
+
 Performing text diffs of binary files
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 

color.c

@@ -202,3 +202,31 @@ int color_fprintf_ln(FILE *fp, const char *color, const char *fmt, ...)
 	va_end(args);
 	return r;
 }
+
+/*
+ * This function splits the buffer by newlines and colors the lines individually.
+ *
+ * Returns 0 on success.
+ */
+int color_fwrite_lines(FILE *fp, const char *color,
+		size_t count, const char *buf)
+{
+	if (!*color)
+		return fwrite(buf, count, 1, fp) != 1;
+	while (count) {
+		char *p = memchr(buf, '\n', count);
+		if (p != buf && (fputs(color, fp) < 0 ||
+				fwrite(buf, p ? p - buf : count, 1, fp) != 1 ||
+				fputs(COLOR_RESET, fp) < 0))
+			return -1;
+		if (!p)
+			return 0;
+		if (fputc('\n', fp) < 0)
+			return -1;
+		count -= p + 1 - buf;
+		buf = p + 1;
+	}
+	return 0;
+}
+
+

color.h

@@ -20,5 +20,6 @@ void color_parse(const char *value, const char *var, char *dst);
 void color_parse_mem(const char *value, int len, const char *var, char *dst);
 int color_fprintf(FILE *fp, const char *color, const char *fmt, ...);
 int color_fprintf_ln(FILE *fp, const char *color, const char *fmt, ...);
+int color_fwrite_lines(FILE *fp, const char *color, size_t count, const char *buf);
 
 #endif /* COLOR_H */

diff.c

@@ -23,6 +23,7 @@ static int diff_detect_rename_default;
 static int diff_rename_limit_default = 200;
 static int diff_suppress_blank_empty;
 int diff_use_color_default = -1;
+static const char *diff_word_regex_cfg;
 static const char *external_diff_cmd_cfg;
 int diff_auto_refresh_index = 1;
 static int diff_mnemonic_prefix;
@@ -92,6 +93,8 @@ int git_diff_ui_config(const char *var, const char *value, void *cb)
 	}
 	if (!strcmp(var, "diff.external"))
 		return git_config_string(&external_diff_cmd_cfg, var, value);
+	if (!strcmp(var, "diff.wordregex"))
+		return git_config_string(&diff_word_regex_cfg, var, value);
 
 	return git_diff_basic_config(var, value, cb);
 }
@@ -321,82 +324,138 @@ static int fill_mmfile(mmfile_t *mf, struct diff_filespec *one)
 struct diff_words_buffer {
 	mmfile_t text;
 	long alloc;
-	long current; /* output pointer */
+	struct diff_words_orig {
-	int suppressed_newline;
+		const char *begin, *end;
+	} *orig;
+	int orig_nr, orig_alloc;
 };
 
 static void diff_words_append(char *line, unsigned long len,
 		struct diff_words_buffer *buffer)
 {
-	if (buffer->text.size + len > buffer->alloc) {
+	ALLOC_GROW(buffer->text.ptr, buffer->text.size + len, buffer->alloc);
-		buffer->alloc = (buffer->text.size + len) * 3 / 2;
-		buffer->text.ptr = xrealloc(buffer->text.ptr, buffer->alloc);
-	}
 	line++;
 	len--;
 	memcpy(buffer->text.ptr + buffer->text.size, line, len);
 	buffer->text.size += len;
+	buffer->text.ptr[buffer->text.size] = '\0';
 }
 
 struct diff_words_data {
 	struct diff_words_buffer minus, plus;
+	const char *current_plus;
 	FILE *file;
+	regex_t *word_regex;
 };
 
-static void print_word(FILE *file, struct diff_words_buffer *buffer, int len, int color,
-		int suppress_newline)
-{
-	const char *ptr;
-	int eol = 0;
-
-	if (len == 0)
-		return;
-
-	ptr  = buffer->text.ptr + buffer->current;
-	buffer->current += len;
-
-	if (ptr[len - 1] == '\n') {
-		eol = 1;
-		len--;
-	}
-
-	fputs(diff_get_color(1, color), file);
-	fwrite(ptr, len, 1, file);
-	fputs(diff_get_color(1, DIFF_RESET), file);
-
-	if (eol) {
-		if (suppress_newline)
-			buffer->suppressed_newline = 1;
-		else
-			putc('\n', file);
-	}
-}
-
 static void fn_out_diff_words_aux(void *priv, char *line, unsigned long len)
 {
 	struct diff_words_data *diff_words = priv;
+	int minus_first, minus_len, plus_first, plus_len;
+	const char *minus_begin, *minus_end, *plus_begin, *plus_end;
 
-	if (diff_words->minus.suppressed_newline) {
+	if (line[0] != '@' || parse_hunk_header(line, len,
-		if (line[0] != '+')
+			&minus_first, &minus_len, &plus_first, &plus_len))
-			putc('\n', diff_words->file);
+		return;
-		diff_words->minus.suppressed_newline = 0;
+
+	/* POSIX requires that first be decremented by one if len == 0... */
+	if (minus_len) {
+		minus_begin = diff_words->minus.orig[minus_first].begin;
+		minus_end =
+			diff_words->minus.orig[minus_first + minus_len - 1].end;
+	} else
+		minus_begin = minus_end =
+			diff_words->minus.orig[minus_first].end;
+
+	if (plus_len) {
+		plus_begin = diff_words->plus.orig[plus_first].begin;
+		plus_end = diff_words->plus.orig[plus_first + plus_len - 1].end;
+	} else
+		plus_begin = plus_end = diff_words->plus.orig[plus_first].end;
+
+	if (diff_words->current_plus != plus_begin)
+		fwrite(diff_words->current_plus,
+				plus_begin - diff_words->current_plus, 1,
+				diff_words->file);
+	if (minus_begin != minus_end)
+		color_fwrite_lines(diff_words->file,
+				diff_get_color(1, DIFF_FILE_OLD),
+				minus_end - minus_begin, minus_begin);
+	if (plus_begin != plus_end)
+		color_fwrite_lines(diff_words->file,
+				diff_get_color(1, DIFF_FILE_NEW),
+				plus_end - plus_begin, plus_begin);
+
+	diff_words->current_plus = plus_end;
+}
+
+/* This function starts looking at *begin, and returns 0 iff a word was found. */
+static int find_word_boundaries(mmfile_t *buffer, regex_t *word_regex,
+		int *begin, int *end)
+{
+	if (word_regex && *begin < buffer->size) {
+		regmatch_t match[1];
+		if (!regexec(word_regex, buffer->ptr + *begin, 1, match, 0)) {
+			char *p = memchr(buffer->ptr + *begin + match[0].rm_so,
+					'\n', match[0].rm_eo - match[0].rm_so);
+			*end = p ? p - buffer->ptr : match[0].rm_eo + *begin;
+			*begin += match[0].rm_so;
+			return *begin >= *end;
+		}
+		return -1;
 	}
 
-	len--;
+	/* find the next word */
-	switch (line[0]) {
+	while (*begin < buffer->size && isspace(buffer->ptr[*begin]))
-		case '-':
+		(*begin)++;
-			print_word(diff_words->file,
+	if (*begin >= buffer->size)
-				   &diff_words->minus, len, DIFF_FILE_OLD, 1);
+		return -1;
-			break;
+
-		case '+':
+	/* find the end of the word */
-			print_word(diff_words->file,
+	*end = *begin + 1;
-				   &diff_words->plus, len, DIFF_FILE_NEW, 0);
+	while (*end < buffer->size && !isspace(buffer->ptr[*end]))
-			break;
+		(*end)++;
-		case ' ':
+
-			print_word(diff_words->file,
+	return 0;
-				   &diff_words->plus, len, DIFF_PLAIN, 0);
+}
-			diff_words->minus.current += len;
+
-			break;
+/*
+ * This function splits the words in buffer->text, stores the list with
+ * newline separator into out, and saves the offsets of the original words
+ * in buffer->orig.
+ */
+static void diff_words_fill(struct diff_words_buffer *buffer, mmfile_t *out,
+		regex_t *word_regex)
+{
+	int i, j;
+	long alloc = 0;
+
+	out->size = 0;
+	out->ptr = NULL;
+
+	/* fake an empty "0th" word */
+	ALLOC_GROW(buffer->orig, 1, buffer->orig_alloc);
+	buffer->orig[0].begin = buffer->orig[0].end = buffer->text.ptr;
+	buffer->orig_nr = 1;
+
+	for (i = 0; i < buffer->text.size; i++) {
+		if (find_word_boundaries(&buffer->text, word_regex, &i, &j))
+			return;
+
+		/* store original boundaries */
+		ALLOC_GROW(buffer->orig, buffer->orig_nr + 1,
+				buffer->orig_alloc);
+		buffer->orig[buffer->orig_nr].begin = buffer->text.ptr + i;
+		buffer->orig[buffer->orig_nr].end = buffer->text.ptr + j;
+		buffer->orig_nr++;
+
+		/* store one word */
+		ALLOC_GROW(out->ptr, out->size + j - i + 1, alloc);
+		memcpy(out->ptr + out->size, buffer->text.ptr + i, j - i);
+		out->ptr[out->size + j - i] = '\n';
+		out->size += j - i + 1;
+
+		i = j - 1;
 	}
 }
 
@@ -407,38 +466,36 @@ static void diff_words_show(struct diff_words_data *diff_words)
 	xdemitconf_t xecfg;
 	xdemitcb_t ecb;
 	mmfile_t minus, plus;
-	int i;
+
+	/* special case: only removal */
+	if (!diff_words->plus.text.size) {
+		color_fwrite_lines(diff_words->file,
+			diff_get_color(1, DIFF_FILE_OLD),
+			diff_words->minus.text.size, diff_words->minus.text.ptr);
+		diff_words->minus.text.size = 0;
+		return;
+	}
+
+	diff_words->current_plus = diff_words->plus.text.ptr;
 
 	memset(&xpp, 0, sizeof(xpp));
 	memset(&xecfg, 0, sizeof(xecfg));
-	minus.size = diff_words->minus.text.size;
+	diff_words_fill(&diff_words->minus, &minus, diff_words->word_regex);
-	minus.ptr = xmalloc(minus.size);
+	diff_words_fill(&diff_words->plus, &plus, diff_words->word_regex);
-	memcpy(minus.ptr, diff_words->minus.text.ptr, minus.size);
-	for (i = 0; i < minus.size; i++)
-		if (isspace(minus.ptr[i]))
-			minus.ptr[i] = '\n';
-	diff_words->minus.current = 0;
-
-	plus.size = diff_words->plus.text.size;
-	plus.ptr = xmalloc(plus.size);
-	memcpy(plus.ptr, diff_words->plus.text.ptr, plus.size);
-	for (i = 0; i < plus.size; i++)
-		if (isspace(plus.ptr[i]))
-			plus.ptr[i] = '\n';
-	diff_words->plus.current = 0;
-
 	xpp.flags = XDF_NEED_MINIMAL;
-	xecfg.ctxlen = diff_words->minus.alloc + diff_words->plus.alloc;
+	/* as only the hunk header will be parsed, we need a 0-context */
+	xecfg.ctxlen = 0;
 	xdi_diff_outf(&minus, &plus, fn_out_diff_words_aux, diff_words,
 		      &xpp, &xecfg, &ecb);
 	free(minus.ptr);
 	free(plus.ptr);
+	if (diff_words->current_plus != diff_words->plus.text.ptr +
+			diff_words->plus.text.size)
+		fwrite(diff_words->current_plus,
+			diff_words->plus.text.ptr + diff_words->plus.text.size
+			- diff_words->current_plus, 1,
+			diff_words->file);
 	diff_words->minus.text.size = diff_words->plus.text.size = 0;
-
-	if (diff_words->minus.suppressed_newline) {
-		putc('\n', diff_words->file);
-		diff_words->minus.suppressed_newline = 0;
-	}
 }
 
 typedef unsigned long (*sane_truncate_fn)(char *line, unsigned long len);
@@ -462,7 +519,10 @@ static void free_diff_words_data(struct emit_callback *ecbdata)
 			diff_words_show(ecbdata->diff_words);
 
 		free (ecbdata->diff_words->minus.text.ptr);
+		free (ecbdata->diff_words->minus.orig);
 		free (ecbdata->diff_words->plus.text.ptr);
+		free (ecbdata->diff_words->plus.orig);
+		free(ecbdata->diff_words->word_regex);
 		free(ecbdata->diff_words);
 		ecbdata->diff_words = NULL;
 	}
@@ -1325,6 +1385,12 @@ static const struct userdiff_funcname *diff_funcname_pattern(struct diff_filespe
 	return one->driver->funcname.pattern ? &one->driver->funcname : NULL;
 }
 
+static const char *userdiff_word_regex(struct diff_filespec *one)
+{
+	diff_filespec_load_driver(one);
+	return one->driver->word_regex;
+}
+
 void diff_set_mnemonic_prefix(struct diff_options *options, const char *a, const char *b)
 {
 	if (!options->a_prefix)
@@ -1485,6 +1551,21 @@ static void builtin_diff(const char *name_a,
 			ecbdata.diff_words =
 				xcalloc(1, sizeof(struct diff_words_data));
 			ecbdata.diff_words->file = o->file;
+			if (!o->word_regex)
+				o->word_regex = userdiff_word_regex(one);
+			if (!o->word_regex)
+				o->word_regex = userdiff_word_regex(two);
+			if (!o->word_regex)
+				o->word_regex = diff_word_regex_cfg;
+			if (o->word_regex) {
+				ecbdata.diff_words->word_regex = (regex_t *)
+					xmalloc(sizeof(regex_t));
+				if (regcomp(ecbdata.diff_words->word_regex,
+						o->word_regex,
+						REG_EXTENDED | REG_NEWLINE))
+					die ("Invalid regular expression: %s",
+							o->word_regex);
+			}
 		}
 		xdi_diff_outf(&mf1, &mf2, fn_out_consume, &ecbdata,
 			      &xpp, &xecfg, &ecb);
@@ -2498,6 +2579,10 @@ int diff_opt_parse(struct diff_options *options, const char **av, int ac)
 		DIFF_OPT_CLR(options, COLOR_DIFF);
 	else if (!strcmp(arg, "--color-words"))
 		options->flags |= DIFF_OPT_COLOR_DIFF | DIFF_OPT_COLOR_DIFF_WORDS;
+	else if (!prefixcmp(arg, "--color-words=")) {
+		options->flags |= DIFF_OPT_COLOR_DIFF | DIFF_OPT_COLOR_DIFF_WORDS;
+		options->word_regex = arg + 14;
+	}
 	else if (!strcmp(arg, "--exit-code"))
 		DIFF_OPT_SET(options, EXIT_WITH_STATUS);
 	else if (!strcmp(arg, "--quiet"))

diff.h

@@ -98,6 +98,7 @@ struct diff_options {
 
 	int stat_width;
 	int stat_name_width;
+	const char *word_regex;
 
 	/* this is set by diffcore for DIFF_FORMAT_PATCH */
 	int found_changes;

t/t4034-diff-words.sh

@@ -0,0 +1,200 @@
+#!/bin/sh
+
+test_description='word diff colors'
+
+. ./test-lib.sh
+
+test_expect_success setup '
+
+	git config diff.color.old red
+	git config diff.color.new green
+
+'
+
+decrypt_color () {
+	sed \
+		-e 's/.\[1m/<WHITE>/g' \
+		-e 's/.\[31m/<RED>/g' \
+		-e 's/.\[32m/<GREEN>/g' \
+		-e 's/.\[36m/<BROWN>/g' \
+		-e 's/.\[m/<RESET>/g'
+}
+
+word_diff () {
+	test_must_fail git diff --no-index "$@" pre post > output &&
+	decrypt_color < output > output.decrypted &&
+	test_cmp expect output.decrypted
+}
+
+cat > pre <<\EOF
+h(4)
+
+a = b + c
+EOF
+
+cat > post <<\EOF
+h(4),hh[44]
+
+a = b + c
+
+aa = a
+
+aeff = aeff * ( aaa )
+EOF
+
+cat > expect <<\EOF
+<WHITE>diff --git a/pre b/post<RESET>
+<WHITE>index 330b04f..5ed8eff 100644<RESET>
+<WHITE>--- a/pre<RESET>
+<WHITE>+++ b/post<RESET>
+<BROWN>@@ -1,3 +1,7 @@<RESET>
+<RED>h(4)<RESET><GREEN>h(4),hh[44]<RESET>
+<RESET>
+a = b + c<RESET>
+
+<GREEN>aa = a<RESET>
+
+<GREEN>aeff = aeff * ( aaa )<RESET>
+EOF
+
+test_expect_success 'word diff with runs of whitespace' '
+
+	word_diff --color-words
+
+'
+
+cat > expect <<\EOF
+<WHITE>diff --git a/pre b/post<RESET>
+<WHITE>index 330b04f..5ed8eff 100644<RESET>
+<WHITE>--- a/pre<RESET>
+<WHITE>+++ b/post<RESET>
+<BROWN>@@ -1,3 +1,7 @@<RESET>
+h(4),<GREEN>hh<RESET>[44]
+<RESET>
+a = b + c<RESET>
+
+<GREEN>aa = a<RESET>
+
+<GREEN>aeff = aeff * ( aaa<RESET> )
+EOF
+cp expect expect.letter-runs-are-words
+
+test_expect_success 'word diff with a regular expression' '
+
+	word_diff --color-words="[a-z]+"
+
+'
+
+test_expect_success 'set a diff driver' '
+	git config diff.testdriver.wordRegex "[^[:space:]]" &&
+	cat <<EOF > .gitattributes
+pre diff=testdriver
+post diff=testdriver
+EOF
+'
+
+test_expect_success 'option overrides .gitattributes' '
+
+	word_diff --color-words="[a-z]+"
+
+'
+
+cat > expect <<\EOF
+<WHITE>diff --git a/pre b/post<RESET>
+<WHITE>index 330b04f..5ed8eff 100644<RESET>
+<WHITE>--- a/pre<RESET>
+<WHITE>+++ b/post<RESET>
+<BROWN>@@ -1,3 +1,7 @@<RESET>
+h(4)<GREEN>,hh[44]<RESET>
+<RESET>
+a = b + c<RESET>
+
+<GREEN>aa = a<RESET>
+
+<GREEN>aeff = aeff * ( aaa )<RESET>
+EOF
+cp expect expect.non-whitespace-is-word
+
+test_expect_success 'use regex supplied by driver' '
+
+	word_diff --color-words
+
+'
+
+test_expect_success 'set diff.wordRegex option' '
+	git config diff.wordRegex "[[:alnum:]]+"
+'
+
+cp expect.letter-runs-are-words expect
+
+test_expect_success 'command-line overrides config' '
+	word_diff --color-words="[a-z]+"
+'
+
+cp expect.non-whitespace-is-word expect
+
+test_expect_success '.gitattributes override config' '
+	word_diff --color-words
+'
+
+test_expect_success 'remove diff driver regex' '
+	git config --unset diff.testdriver.wordRegex
+'
+
+cat > expect <<\EOF
+<WHITE>diff --git a/pre b/post<RESET>
+<WHITE>index 330b04f..5ed8eff 100644<RESET>
+<WHITE>--- a/pre<RESET>
+<WHITE>+++ b/post<RESET>
+<BROWN>@@ -1,3 +1,7 @@<RESET>
+h(4),<GREEN>hh[44<RESET>]
+<RESET>
+a = b + c<RESET>
+
+<GREEN>aa = a<RESET>
+
+<GREEN>aeff = aeff * ( aaa<RESET> )
+EOF
+
+test_expect_success 'use configured regex' '
+	word_diff --color-words
+'
+
+echo 'aaa (aaa)' > pre
+echo 'aaa (aaa) aaa' > post
+
+cat > expect <<\EOF
+<WHITE>diff --git a/pre b/post<RESET>
+<WHITE>index c29453b..be22f37 100644<RESET>
+<WHITE>--- a/pre<RESET>
+<WHITE>+++ b/post<RESET>
+<BROWN>@@ -1 +1 @@<RESET>
+aaa (aaa) <GREEN>aaa<RESET>
+EOF
+
+test_expect_success 'test parsing words for newline' '
+
+	word_diff --color-words="a+"
+
+
+'
+
+echo '(:' > pre
+echo '(' > post
+
+cat > expect <<\EOF
+<WHITE>diff --git a/pre b/post<RESET>
+<WHITE>index 289cb9d..2d06f37 100644<RESET>
+<WHITE>--- a/pre<RESET>
+<WHITE>+++ b/post<RESET>
+<BROWN>@@ -1 +1 @@<RESET>
+(<RED>:<RESET>
+EOF
+
+test_expect_success 'test when words are only removed at the end' '
+
+	word_diff --color-words=.
+
+'
+
+test_done

userdiff.c

@@ -6,14 +6,20 @@ static struct userdiff_driver *drivers;
 static int ndrivers;
 static int drivers_alloc;
 
-#define FUNCNAME(name, pattern) \
+#define PATTERNS(name, pattern, word_regex)			\
-	{ name, NULL, -1, { pattern, REG_EXTENDED } }
+	{ name, NULL, -1, { pattern, REG_EXTENDED }, word_regex }
 static struct userdiff_driver builtin_drivers[] = {
-FUNCNAME("html", "^[ \t]*(<[Hh][1-6][ \t].*>.*)$"),
+PATTERNS("html", "^[ \t]*(<[Hh][1-6][ \t].*>.*)$",
-FUNCNAME("java",
+	 "[^<>= \t]+|[^[:space:]]|[\x80-\xff]+"),
+PATTERNS("java",
 	 "!^[ \t]*(catch|do|for|if|instanceof|new|return|switch|throw|while)\n"
-	 "^[ \t]*(([ \t]*[A-Za-z_][A-Za-z_0-9]*){2,}[ \t]*\\([^;]*)$"),
+	 "^[ \t]*(([ \t]*[A-Za-z_][A-Za-z_0-9]*){2,}[ \t]*\\([^;]*)$",
-FUNCNAME("objc",
+	 "[a-zA-Z_][a-zA-Z0-9_]*"
+	 "|[-+0-9.e]+[fFlL]?|0[xXbB]?[0-9a-fA-F]+[lL]?"
+	 "|[-+*/<>%&^|=!]="
+	 "|--|\\+\\+|<<=?|>>>?=?|&&|\\|\\|"
+	 "|[^[:space:]]|[\x80-\xff]+"),
+PATTERNS("objc",
 	 /* Negate C statements that can look like functions */
 	 "!^[ \t]*(do|for|if|else|return|switch|while)\n"
 	 /* Objective-C methods */
@@ -21,20 +27,60 @@ FUNCNAME("objc",
 	 /* C functions */
 	 "^[ \t]*(([ \t]*[A-Za-z_][A-Za-z_0-9]*){2,}[ \t]*\\([^;]*)$\n"
 	 /* Objective-C class/protocol definitions */
-	 "^(@(implementation|interface|protocol)[ \t].*)$"),
+	 "^(@(implementation|interface|protocol)[ \t].*)$",
-FUNCNAME("pascal",
+	 /* -- */
+	 "[a-zA-Z_][a-zA-Z0-9_]*"
+	 "|[-+0-9.e]+[fFlL]?|0[xXbB]?[0-9a-fA-F]+[lL]?"
+	 "|[-+*/<>%&^|=!]=|--|\\+\\+|<<=?|>>=?|&&|\\|\\||::|->"
+	 "|[^[:space:]]|[\x80-\xff]+"),
+PATTERNS("pascal",
 	 "^((procedure|function|constructor|destructor|interface|"
 		"implementation|initialization|finalization)[ \t]*.*)$"
 	 "\n"
-	 "^(.*=[ \t]*(class|record).*)$"),
+	 "^(.*=[ \t]*(class|record).*)$",
-FUNCNAME("php", "^[\t ]*((function|class).*)"),
+	 /* -- */
-FUNCNAME("python", "^[ \t]*((class|def)[ \t].*)$"),
+	 "[a-zA-Z_][a-zA-Z0-9_]*"
-FUNCNAME("ruby", "^[ \t]*((class|module|def)[ \t].*)$"),
+	 "|[-+0-9.e]+|0[xXbB]?[0-9a-fA-F]+"
-FUNCNAME("bibtex", "(@[a-zA-Z]{1,}[ \t]*\\{{0,1}[ \t]*[^ \t\"@',\\#}{~%]*).*$"),
+	 "|<>|<=|>=|:=|\\.\\."
-FUNCNAME("tex", "^(\\\\((sub)*section|chapter|part)\\*{0,1}\\{.*)$"),
+	 "|[^[:space:]]|[\x80-\xff]+"),
+PATTERNS("php", "^[\t ]*((function|class).*)",
+	 /* -- */
+	 "[a-zA-Z_][a-zA-Z0-9_]*"
+	 "|[-+0-9.e]+|0[xXbB]?[0-9a-fA-F]+"
+	 "|[-+*/<>%&^|=!.]=|--|\\+\\+|<<=?|>>=?|===|&&|\\|\\||::|->"
+	 "|[^[:space:]]|[\x80-\xff]+"),
+PATTERNS("python", "^[ \t]*((class|def)[ \t].*)$",
+	 /* -- */
+	 "[a-zA-Z_][a-zA-Z0-9_]*"
+	 "|[-+0-9.e]+[jJlL]?|0[xX]?[0-9a-fA-F]+[lL]?"
+	 "|[-+*/<>%&^|=!]=|//=?|<<=?|>>=?|\\*\\*=?"
+	 "|[^[:space:]|[\x80-\xff]+"),
+	 /* -- */
+PATTERNS("ruby", "^[ \t]*((class|module|def)[ \t].*)$",
+	 /* -- */
+	 "(@|@@|\\$)?[a-zA-Z_][a-zA-Z0-9_]*"
+	 "|[-+0-9.e]+|0[xXbB]?[0-9a-fA-F]+|\\?(\\\\C-)?(\\\\M-)?."
+	 "|//=?|[-+*/<>%&^|=!]=|<<=?|>>=?|===|\\.{1,3}|::|[!=]~"
+	 "|[^[:space:]|[\x80-\xff]+"),
+PATTERNS("bibtex", "(@[a-zA-Z]{1,}[ \t]*\\{{0,1}[ \t]*[^ \t\"@',\\#}{~%]*).*$",
+	 "[={}\"]|[^={}\" \t]+"),
+PATTERNS("tex", "^(\\\\((sub)*section|chapter|part)\\*{0,1}\\{.*)$",
+	 "\\\\[a-zA-Z@]+|\\\\.|[a-zA-Z0-9\x80-\xff]+|[^[:space:]]"),
+PATTERNS("cpp",
+	 /* Jump targets or access declarations */
+	 "!^[ \t]*[A-Za-z_][A-Za-z_0-9]*:.*$\n"
+	 /* C/++ functions/methods at top level */
+	 "^([A-Za-z_][A-Za-z_0-9]*([ \t]+[A-Za-z_][A-Za-z_0-9]*([ \t]*::[ \t]*[^[:space:]]+)?){1,}[ \t]*\\([^;]*)$\n"
+	 /* compound type at top level */
+	 "^((struct|class|enum)[^;]*)$",
+	 /* -- */
+	 "[a-zA-Z_][a-zA-Z0-9_]*"
+	 "|[-+0-9.e]+[fFlL]?|0[xXbB]?[0-9a-fA-F]+[lL]?"
+	 "|[-+*/<>%&^|=!]=|--|\\+\\+|<<=?|>>=?|&&|\\|\\||::|->"
+	 "|[^[:space:]]|[\x80-\xff]+"),
 { "default", NULL, -1, { NULL, 0 } },
 };
-#undef FUNCNAME
+#undef PATTERNS
 
 static struct userdiff_driver driver_true = {
 	"diff=true",
@@ -134,6 +180,8 @@ int userdiff_config(const char *k, const char *v)
 		return parse_string(&drv->external, k, v);
 	if ((drv = parse_driver(k, v, "textconv")))
 		return parse_string(&drv->textconv, k, v);
+	if ((drv = parse_driver(k, v, "wordregex")))
+		return parse_string(&drv->word_regex, k, v);
 
 	return 0;
 }

userdiff.h

@@ -11,6 +11,7 @@ struct userdiff_driver {
 	const char *external;
 	int binary;
 	struct userdiff_funcname funcname;
+	const char *word_regex;
 	const char *textconv;
 };