userdiff: add built-in pattern for CSS

CSS is widely used, motivating it being included as a built-in pattern.

It must be noted that the word_regex for CSS (i.e. the regex defining
what is a word in the language) does not consider '.' and '#' characters
(in CSS selectors) to be part of the word. This behavior is documented
by the test t/t4018/css-rule.
The logic behind this behavior is the following: identifiers in CSS
selectors are identifiers in a HTML/XML document. Therefore, the '.'/'#'
character are not part of the identifier, but an indicator of the nature
of the identifier in HTML/XML (class or id). Diffing ".class1" and
".class2" must show that the class name is changed, but we still are
selecting a class.

Logic behind the "pattern" regex is:
    1. reject lines ending with a colon/semicolon (properties)
    2. if a line begins with a name in column 1, pick the whole line

Credits to Johannes Sixt (j6t@kdbg.org) for the pattern regex and most
of the tests.

Signed-off-by: William Duclot <william.duclot@ensimag.grenoble-inp.fr>
Signed-off-by: Matthieu Moy <matthieu.moy@grenoble-inp.fr>
Reviewed-by: Johannes Sixt <j6t@kdbg.org>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

15 files changed, 90 insertions, 0 deletions

diff --git a/Documentation/gitattributes.txt b/Documentation/gitattributes.txt
index e3b1de8033..8882a3e914 100644
--- a/Documentation/gitattributes.txt
+++ b/Documentation/gitattributes.txt
@@ -525,6 +525,8 @@ patterns are available:
 
 - `csharp` suitable for source code in the C# language.
 
+- `css` suitable for cascading style sheets.
+
 - `fortran` suitable for source code in the Fortran language.
 
 - `fountain` suitable for Fountain documents.
diff --git a/t/t4018-diff-funcname.sh b/t/t4018-diff-funcname.sh
index 67373dc44e..1795ffc3aa 100755
--- a/t/t4018-diff-funcname.sh
+++ b/t/t4018-diff-funcname.sh
@@ -30,6 +30,7 @@ diffpatterns="
 	bibtex
 	cpp
 	csharp
+	css
 	fortran
 	fountain
 	html
diff --git a/t/t4018/css-brace-in-col-1 b/t/t4018/css-brace-in-col-1
new file mode 100644
index 0000000000..7831577506
--- /dev/null
+++ b/t/t4018/css-brace-in-col-1
@@ -0,0 +1,5 @@
+RIGHT label.control-label
+{
+    margin-top: 10px!important;
+    border : 10px ChangeMe #C6C6C6;
+}
diff --git a/t/t4018/css-colon-eol b/t/t4018/css-colon-eol
new file mode 100644
index 0000000000..5a30553d29
--- /dev/null
+++ b/t/t4018/css-colon-eol
@@ -0,0 +1,4 @@
+RIGHT h1 {
+color:
+ChangeMe;
+}
diff --git a/t/t4018/css-colon-selector b/t/t4018/css-colon-selector
new file mode 100644
index 0000000000..c6d71fb42d
--- /dev/null
+++ b/t/t4018/css-colon-selector
@@ -0,0 +1,5 @@
+RIGHT a:hover {
+    margin-top:
+    10px!important;
+    border : 10px ChangeMe #C6C6C6;
+}
diff --git a/t/t4018/css-common b/t/t4018/css-common
new file mode 100644
index 0000000000..84ed754b33
--- /dev/null
+++ b/t/t4018/css-common
@@ -0,0 +1,4 @@
+RIGHT label.control-label {
+    margin-top: 10px!important;
+    border : 10px ChangeMe #C6C6C6;
+}
diff --git a/t/t4018/css-long-selector-list b/t/t4018/css-long-selector-list
new file mode 100644
index 0000000000..7ccd25d9ed
--- /dev/null
+++ b/t/t4018/css-long-selector-list
@@ -0,0 +1,6 @@
+p.header,
+label.control-label,
+div ul#RIGHT {
+    margin-top: 10px!important;
+    border : 10px ChangeMe #C6C6C6;
+}
diff --git a/t/t4018/css-prop-sans-indent b/t/t4018/css-prop-sans-indent
new file mode 100644
index 0000000000..a9e3c86b3c
--- /dev/null
+++ b/t/t4018/css-prop-sans-indent
@@ -0,0 +1,5 @@
+RIGHT, label.control-label {
+margin-top: 10px!important;
+padding: 0;
+border : 10px ChangeMe #C6C6C6;
+}
diff --git a/t/t4018/css-short-selector-list b/t/t4018/css-short-selector-list
new file mode 100644
index 0000000000..6a0bdee336
--- /dev/null
+++ b/t/t4018/css-short-selector-list
@@ -0,0 +1,4 @@
+label.control, div ul#RIGHT {
+    margin-top: 10px!important;
+    border : 10px ChangeMe #C6C6C6;
+}
diff --git a/t/t4018/css-trailing-space b/t/t4018/css-trailing-space
new file mode 100644
index 0000000000..32b5606c70
--- /dev/null
+++ b/t/t4018/css-trailing-space
@@ -0,0 +1,5 @@
+RIGHT label.control-label {
+    margin:10px;   
+    padding:10px;
+    border : 10px ChangeMe #C6C6C6;
+}
diff --git a/t/t4034-diff-words.sh b/t/t4034-diff-words.sh
index f2f55fc51c..912df91226 100755
--- a/t/t4034-diff-words.sh
+++ b/t/t4034-diff-words.sh
@@ -302,6 +302,7 @@ test_language_driver ada
 test_language_driver bibtex
 test_language_driver cpp
 test_language_driver csharp
+test_language_driver css
 test_language_driver fortran
 test_language_driver html
 test_language_driver java
diff --git a/t/t4034/css/expect b/t/t4034/css/expect
new file mode 100644
index 0000000000..ed10393bda
--- /dev/null
+++ b/t/t4034/css/expect
@@ -0,0 +1,16 @@
+<BOLD>diff --git a/pre b/post<RESET>
+<BOLD>index b8ae0bb..fe500b7 100644<RESET>
+<BOLD>--- a/pre<RESET>
+<BOLD>+++ b/post<RESET>
+<CYAN>@@ -1,10 +1,10 @@<RESET>
+.<RED>class-form<RESET><GREEN>other-form<RESET> label.control-label {
+    margin-top: <RED>10<RESET><GREEN>15<RESET>px!important;
+    border : 10px <RED>dashed<RESET><GREEN>dotted<RESET> #C6C6C6;
+}<RESET>
+<RED>#CCCCCC<RESET><GREEN>#CCCCCB<RESET>
+10em<RESET>
+<RED>padding-bottom<RESET><GREEN>margin-left<RESET>
+150<RED>px<RESET><GREEN>em<RESET>
+10px
+<RED>!important<RESET>
+<RED>div<RESET><GREEN>li<RESET>.class#id
diff --git a/t/t4034/css/post b/t/t4034/css/post
new file mode 100644
index 0000000000..fe500b7a4f
--- /dev/null
+++ b/t/t4034/css/post
@@ -0,0 +1,10 @@
+.other-form label.control-label {
+    margin-top: 15px!important;
+    border : 10px dotted #C6C6C6;
+}
+#CCCCCB
+10em
+margin-left
+150em
+10px
+li.class#id
diff --git a/t/t4034/css/pre b/t/t4034/css/pre
new file mode 100644
index 0000000000..b8ae0bb48f
--- /dev/null
+++ b/t/t4034/css/pre
@@ -0,0 +1,10 @@
+.class-form label.control-label {
+    margin-top: 10px!important;
+    border : 10px dashed #C6C6C6;
+}
+#CCCCCC
+10em
+padding-bottom
+150px
+10px!important
+div.class#id
diff --git a/userdiff.c b/userdiff.c
index 6bf2505994..2125d6da26 100644
--- a/userdiff.c
+++ b/userdiff.c
@@ -148,6 +148,18 @@ PATTERNS("csharp",
 	 "[a-zA-Z_][a-zA-Z0-9_]*"
 	 "|[-+0-9.e]+[fFlL]?|0[xXbB]?[0-9a-fA-F]+[lL]?"
 	 "|[-+*/<>%&^|=!]=|--|\\+\\+|<<=?|>>=?|&&|\\|\\||::|->"),
+IPATTERN("css",
+	 "![:;][[:space:]]*$\n"
+	 "^[_a-z0-9].*$",
+	 /* -- */
+	 /*
+	  * This regex comes from W3C CSS specs. Should theoretically also
+	  * allow ISO 10646 characters U+00A0 and higher,
+	  * but they are not handled in this regex.
+	  */
+	 "-?[_a-zA-Z][-_a-zA-Z0-9]*" /* identifiers */
+	 "|-?[0-9]+|\\#[0-9a-fA-F]+" /* numbers */
+),
 { "default", NULL, -1, { NULL, 0 } },
 };
 #undef PATTERNS