From d74e78602e3d562f5db64d553d4be21c201ef7b3 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Marc-Andr=C3=A9=20Lureau?= Date: Fri, 17 May 2019 01:58:15 +0200 Subject: userdiff: add built-in pattern for rust MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This adds xfuncname and word_regex patterns for Rust, a quite popular programming language. It also includes test cases for the xfuncname regex (t4018) and updated documentation. The word_regex pattern finds identifiers, integers, floats and operators, according to the Rust Reference Book. Cc: Johannes Sixt Signed-off-by: Marc-André Lureau Signed-off-by: Junio C Hamano --- userdiff.c | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'userdiff.c') diff --git a/userdiff.c b/userdiff.c index 3a78fbf504..8d7e62e2a5 100644 --- a/userdiff.c +++ b/userdiff.c @@ -130,6 +130,13 @@ 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}|::|[!=]~"), +PATTERNS("rust", + "^[\t ]*((pub(\\([^\\)]+\\))?[\t ]+)?((async|const|unsafe|extern([\t ]+\"[^\"]+\"))[\t ]+)?(struct|enum|union|mod|trait|fn|impl(<.+>)?)[ \t]+[^;]*)$", + /* -- */ + "[a-zA-Z_][a-zA-Z0-9_]*" + "|[-+_0-9.eE]+(f32|f64|u8|u16|u32|u64|u128|usize|i8|i16|i32|i64|i128|isize)?" + "|0[box]?[0-9a-fA-F_]+(u8|u16|u32|u64|u128|usize|i8|i16|i32|i64|i128|isize)?" + "|[-+*\\/<>%&^|=!:]=|<<=?|>>=?|&&|\\|\\||->|=>|\\.{2}=|\\.{3}|::"), PATTERNS("bibtex", "(@[a-zA-Z]{1,}[ \t]*\\{{0,1}[ \t]*[^ \t\"@',\\#}{~%]*).*$", "[={}\"]|[^={}\" \t]+"), PATTERNS("tex", "^(\\\\((sub)*section|chapter|part)\\*{0,1}\\{.*)$", -- cgit v1.2.3 From 33be7b38c23fbbaf75197f6150323e0d4c84bf12 Mon Sep 17 00:00:00 2001 From: Johannes Sixt Date: Thu, 30 May 2019 18:44:35 +0200 Subject: userdiff: two simplifications of patterns for rust - Do not enforce (but assume) syntactic correctness of language constructs that go into hunk headers: we only want to ensure that the keywords actually are words and not just the initial part of some identifier. - In the word regex, match numbers only when they begin with a digit, but then be liberal in what follows, assuming that the text that is matched is syntactially correct. Signed-off-by: Johannes Sixt Signed-off-by: Junio C Hamano --- userdiff.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'userdiff.c') diff --git a/userdiff.c b/userdiff.c index 8d7e62e2a5..2bcf105caf 100644 --- a/userdiff.c +++ b/userdiff.c @@ -131,11 +131,10 @@ PATTERNS("ruby", "^[ \t]*((class|module|def)[ \t].*)$", "|[-+0-9.e]+|0[xXbB]?[0-9a-fA-F]+|\\?(\\\\C-)?(\\\\M-)?." "|//=?|[-+*/<>%&^|=!]=|<<=?|>>=?|===|\\.{1,3}|::|[!=]~"), PATTERNS("rust", - "^[\t ]*((pub(\\([^\\)]+\\))?[\t ]+)?((async|const|unsafe|extern([\t ]+\"[^\"]+\"))[\t ]+)?(struct|enum|union|mod|trait|fn|impl(<.+>)?)[ \t]+[^;]*)$", + "^[\t ]*((pub(\\([^\\)]+\\))?[\t ]+)?((async|const|unsafe|extern([\t ]+\"[^\"]+\"))[\t ]+)?(struct|enum|union|mod|trait|fn|impl)[< \t]+[^;]*)$", /* -- */ "[a-zA-Z_][a-zA-Z0-9_]*" - "|[-+_0-9.eE]+(f32|f64|u8|u16|u32|u64|u128|usize|i8|i16|i32|i64|i128|isize)?" - "|0[box]?[0-9a-fA-F_]+(u8|u16|u32|u64|u128|usize|i8|i16|i32|i64|i128|isize)?" + "|[0-9][0-9_a-fA-Fiosuxz]*(\\.([0-9]*[eE][+-]?)?[0-9_fF]*)?" "|[-+*\\/<>%&^|=!:]=|<<=?|>>=?|&&|\\|\\||->|=>|\\.{2}=|\\.{3}|::"), PATTERNS("bibtex", "(@[a-zA-Z]{1,}[ \t]*\\{{0,1}[ \t]*[^ \t\"@',\\#}{~%]*).*$", "[={}\"]|[^={}\" \t]+"), -- cgit v1.2.3