git/grep.h

121 строка
2.7 KiB
C
Исходник Обычный вид История

#ifndef GREP_H
#define GREP_H
#include "color.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>
2008-09-05 09:15:02 +04:00
enum grep_header_field {
GREP_HEADER_AUTHOR = 0,
GREP_HEADER_COMMITTER
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>
2008-09-05 09:15:02 +04:00
};
#define GREP_HEADER_FIELD_MAX (GREP_HEADER_COMMITTER + 1)
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>
2008-09-05 09:15:02 +04:00
struct grep_pat {
struct grep_pat *next;
const char *origin;
int no;
enum grep_pat_token token;
const char *pattern;
size_t patternlen;
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>
2008-09-05 09:15:02 +04:00
enum grep_header_field field;
regex_t regexp;
unsigned fixed:1;
unsigned ignore_case:1;
unsigned word_regexp:1;
};
enum grep_expr_node {
GREP_NODE_ATOM,
GREP_NODE_NOT,
GREP_NODE_AND,
GREP_NODE_TRUE,
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_pat *header_list;
struct grep_pat **header_tail;
struct grep_expr *pattern_expression;
const char *prefix;
int prefix_length;
regex_t regexp;
int linenum;
int invert;
int ignore_case;
int status_only;
int name_only;
int unmatch_name_only;
int count;
int word_regexp;
int fixed;
int all_match;
#define GREP_BINARY_DEFAULT 0
#define GREP_BINARY_NOMATCH 1
#define GREP_BINARY_TEXT 2
int binary;
int extended;
int relative;
int pathname;
int null_following_name;
int color;
int max_depth;
int funcname;
char color_context[COLOR_MAXLEN];
char color_filename[COLOR_MAXLEN];
char color_function[COLOR_MAXLEN];
char color_lineno[COLOR_MAXLEN];
char color_match[COLOR_MAXLEN];
char color_selected[COLOR_MAXLEN];
char color_sep[COLOR_MAXLEN];
int regflags;
unsigned pre_context;
unsigned post_context;
unsigned last_shown;
int show_hunk_mark;
void *priv;
void (*output)(struct grep_opt *opt, const void *data, size_t size);
void *output_priv;
};
extern void append_grep_pat(struct grep_opt *opt, const char *pat, size_t patlen, const char *origin, int no, enum grep_pat_token t);
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>
2008-09-05 09:15:02 +04:00
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);
extern struct grep_opt *grep_opt_dup(const struct grep_opt *opt);
extern int grep_threads_ok(const struct grep_opt *opt);
#endif