|
|
|
#ifndef GREP_H
|
|
|
|
#define GREP_H
|
|
|
|
|
|
|
|
enum grep_pat_token {
|
|
|
|
GREP_PATTERN,
|
|
|
|
GREP_PATTERN_HEAD,
|
|
|
|
GREP_PATTERN_BODY,
|
|
|
|
GREP_AND,
|
|
|
|
GREP_OPEN_PAREN,
|
|
|
|
GREP_CLOSE_PAREN,
|
|
|
|
GREP_NOT,
|
|
|
|
GREP_OR,
|
|
|
|
};
|
|
|
|
|
|
|
|
enum grep_context {
|
|
|
|
GREP_CONTEXT_HEAD,
|
|
|
|
GREP_CONTEXT_BODY,
|
|
|
|
};
|
|
|
|
|
log --author/--committer: really match only with name part
When we tried to find commits done by AUTHOR, the first implementation
tried to pattern match a line with "^author .*AUTHOR", which later was
enhanced to strip leading caret and look for "^author AUTHOR" when the
search pattern was anchored at the left end (i.e. --author="^AUTHOR").
This had a few problems:
* When looking for fixed strings (e.g. "git log -F --author=x --grep=y"),
the regexp internally used "^author .*x" would never match anything;
* To match at the end (e.g. "git log --author='google.com>$'"), the
generated regexp has to also match the trailing timestamp part the
commit header lines have. Also, in order to determine if the '$' at
the end means "match at the end of the line" or just a literal dollar
sign (probably backslash-quoted), we would need to parse the regexp
ourselves.
An earlier alternative tried to make sure that a line matches "^author "
(to limit by field name) and the user supplied pattern at the same time.
While it solved the -F problem by introducing a special override for
matching the "^author ", it did not solve the trailing timestamp nor tail
match problem. It also would have matched every commit if --author=author
was asked for, not because the author's email part had this string, but
because every commit header line that talks about the author begins with
that field name, regardleses of who wrote it.
Instead of piling more hacks on top of hacks, this rethinks the grep
machinery that is used to look for strings in the commit header, and makes
sure that (1) field name matches literally at the beginning of the line,
followed by a SP, and (2) the user supplied pattern is matched against the
remainder of the line, excluding the trailing timestamp data.
Signed-off-by: Junio C Hamano <gitster@pobox.com>
16 years ago
|
|
|
enum grep_header_field {
|
|
|
|
GREP_HEADER_AUTHOR = 0,
|
|
|
|
GREP_HEADER_COMMITTER,
|
|
|
|
};
|
|
|
|
|
|
|
|
struct grep_pat {
|
|
|
|
struct grep_pat *next;
|
|
|
|
const char *origin;
|
|
|
|
int no;
|
|
|
|
enum grep_pat_token token;
|
|
|
|
const char *pattern;
|
log --author/--committer: really match only with name part
When we tried to find commits done by AUTHOR, the first implementation
tried to pattern match a line with "^author .*AUTHOR", which later was
enhanced to strip leading caret and look for "^author AUTHOR" when the
search pattern was anchored at the left end (i.e. --author="^AUTHOR").
This had a few problems:
* When looking for fixed strings (e.g. "git log -F --author=x --grep=y"),
the regexp internally used "^author .*x" would never match anything;
* To match at the end (e.g. "git log --author='google.com>$'"), the
generated regexp has to also match the trailing timestamp part the
commit header lines have. Also, in order to determine if the '$' at
the end means "match at the end of the line" or just a literal dollar
sign (probably backslash-quoted), we would need to parse the regexp
ourselves.
An earlier alternative tried to make sure that a line matches "^author "
(to limit by field name) and the user supplied pattern at the same time.
While it solved the -F problem by introducing a special override for
matching the "^author ", it did not solve the trailing timestamp nor tail
match problem. It also would have matched every commit if --author=author
was asked for, not because the author's email part had this string, but
because every commit header line that talks about the author begins with
that field name, regardleses of who wrote it.
Instead of piling more hacks on top of hacks, this rethinks the grep
machinery that is used to look for strings in the commit header, and makes
sure that (1) field name matches literally at the beginning of the line,
followed by a SP, and (2) the user supplied pattern is matched against the
remainder of the line, excluding the trailing timestamp data.
Signed-off-by: Junio C Hamano <gitster@pobox.com>
16 years ago
|
|
|
enum grep_header_field field;
|
|
|
|
regex_t regexp;
|
|
|
|
};
|
|
|
|
|
|
|
|
enum grep_expr_node {
|
|
|
|
GREP_NODE_ATOM,
|
|
|
|
GREP_NODE_NOT,
|
|
|
|
GREP_NODE_AND,
|
|
|
|
GREP_NODE_OR,
|
|
|
|
};
|
|
|
|
|
|
|
|
struct grep_expr {
|
|
|
|
enum grep_expr_node node;
|
|
|
|
unsigned hit;
|
|
|
|
union {
|
|
|
|
struct grep_pat *atom;
|
|
|
|
struct grep_expr *unary;
|
|
|
|
struct {
|
|
|
|
struct grep_expr *left;
|
|
|
|
struct grep_expr *right;
|
|
|
|
} binary;
|
|
|
|
} u;
|
|
|
|
};
|
|
|
|
|
|
|
|
struct grep_opt {
|
|
|
|
struct grep_pat *pattern_list;
|
|
|
|
struct grep_pat **pattern_tail;
|
|
|
|
struct grep_expr *pattern_expression;
|
|
|
|
int prefix_length;
|
|
|
|
regex_t regexp;
|
|
|
|
unsigned linenum:1;
|
|
|
|
unsigned invert:1;
|
|
|
|
unsigned status_only:1;
|
|
|
|
unsigned name_only:1;
|
|
|
|
unsigned unmatch_name_only:1;
|
|
|
|
unsigned count:1;
|
|
|
|
unsigned word_regexp:1;
|
|
|
|
unsigned fixed:1;
|
|
|
|
unsigned all_match:1;
|
|
|
|
#define GREP_BINARY_DEFAULT 0
|
|
|
|
#define GREP_BINARY_NOMATCH 1
|
|
|
|
#define GREP_BINARY_TEXT 2
|
|
|
|
unsigned binary:2;
|
|
|
|
unsigned extended:1;
|
|
|
|
unsigned relative:1;
|
|
|
|
unsigned pathname:1;
|
|
|
|
unsigned null_following_name:1;
|
|
|
|
int regflags;
|
|
|
|
unsigned pre_context;
|
|
|
|
unsigned post_context;
|
|
|
|
};
|
|
|
|
|
|
|
|
extern void append_grep_pattern(struct grep_opt *opt, const char *pat, const char *origin, int no, enum grep_pat_token t);
|
log --author/--committer: really match only with name part
When we tried to find commits done by AUTHOR, the first implementation
tried to pattern match a line with "^author .*AUTHOR", which later was
enhanced to strip leading caret and look for "^author AUTHOR" when the
search pattern was anchored at the left end (i.e. --author="^AUTHOR").
This had a few problems:
* When looking for fixed strings (e.g. "git log -F --author=x --grep=y"),
the regexp internally used "^author .*x" would never match anything;
* To match at the end (e.g. "git log --author='google.com>$'"), the
generated regexp has to also match the trailing timestamp part the
commit header lines have. Also, in order to determine if the '$' at
the end means "match at the end of the line" or just a literal dollar
sign (probably backslash-quoted), we would need to parse the regexp
ourselves.
An earlier alternative tried to make sure that a line matches "^author "
(to limit by field name) and the user supplied pattern at the same time.
While it solved the -F problem by introducing a special override for
matching the "^author ", it did not solve the trailing timestamp nor tail
match problem. It also would have matched every commit if --author=author
was asked for, not because the author's email part had this string, but
because every commit header line that talks about the author begins with
that field name, regardleses of who wrote it.
Instead of piling more hacks on top of hacks, this rethinks the grep
machinery that is used to look for strings in the commit header, and makes
sure that (1) field name matches literally at the beginning of the line,
followed by a SP, and (2) the user supplied pattern is matched against the
remainder of the line, excluding the trailing timestamp data.
Signed-off-by: Junio C Hamano <gitster@pobox.com>
16 years ago
|
|
|
extern void append_header_grep_pattern(struct grep_opt *, enum grep_header_field, const char *);
|
|
|
|
extern void compile_grep_patterns(struct grep_opt *opt);
|
|
|
|
extern void free_grep_patterns(struct grep_opt *opt);
|
|
|
|
extern int grep_buffer(struct grep_opt *opt, const char *name, char *buf, unsigned long size);
|
|
|
|
|
|
|
|
#endif
|