X-Git-Url: https://git.cameronkatri.com/cgit.git/blobdiff_plain/2122c696a34133a616b9ec6d72abe9eb89e728aa..c4fbb99cee30fa295e240b429b2dc7e8ad83d535:/parsing.c diff --git a/parsing.c b/parsing.c index 5093b8b..12453c2 100644 --- a/parsing.c +++ b/parsing.c @@ -1,6 +1,6 @@ -/* config.c: parsing of config files +/* parsing.c: parsing of config files * - * Copyright (C) 2006 Lars Hjemli + * Copyright (C) 2006-2014 cgit Development Team * * Licensed under GNU General Public License v2 * (see COPYING for full license text) @@ -8,130 +8,6 @@ #include "cgit.h" -int next_char(FILE *f) -{ - int c = fgetc(f); - if (c=='\r') { - c = fgetc(f); - if (c!='\n') { - ungetc(c, f); - c = '\r'; - } - } - return c; -} - -void skip_line(FILE *f) -{ - int c; - - while((c=next_char(f)) && c!='\n' && c!=EOF) - ; -} - -int read_config_line(FILE *f, char *line, const char **value, int bufsize) -{ - int i = 0, isname = 0; - - *value = NULL; - while(i 8) - return -1; - if (!(f = fopen(filename, "r"))) - return -1; - nesting++; - while((len = read_config_line(f, line, &value, sizeof(line))) > 0) - (*fn)(line, value); - nesting--; - fclose(f); - return 0; -} - -char *convert_query_hexchar(char *txt) -{ - int d1, d2; - if (strlen(txt) < 3) { - *txt = '\0'; - return txt-1; - } - d1 = hextoint(*(txt+1)); - d2 = hextoint(*(txt+2)); - if (d1<0 || d2<0) { - strcpy(txt, txt+3); - return txt-1; - } else { - *txt = d1 * 16 + d2; - strcpy(txt+1, txt+3); - return txt; - } -} - -int cgit_parse_query(char *txt, configfn fn) -{ - char *t, *value = NULL, c; - - if (!txt) - return 0; - - t = txt = xstrdup(txt); - - while((c=*t) != '\0') { - if (c=='=') { - *t = '\0'; - value = t+1; - } else if (c=='+') { - *t = ' '; - } else if (c=='%') { - t = convert_query_hexchar(t); - } else if (c=='&') { - *t = '\0'; - (*fn)(txt, value); - txt = t+1; - value = NULL; - } - t++; - } - if (t!=txt) - (*fn)(txt, value); - return 0; -} - /* * url syntax: [repo ['/' cmd [ '/' path]]] * repo: any valid repo url, may contain '/' @@ -141,192 +17,209 @@ int cgit_parse_query(char *txt, configfn fn) */ void cgit_parse_url(const char *url) { - char *cmd, *p; + char *c, *cmd, *p; + struct cgit_repo *repo; - cgit_repo = NULL; if (!url || url[0] == '\0') return; - cgit_repo = cgit_get_repoinfo(url); - if (cgit_repo) { - cgit_query_repo = cgit_repo->url; + ctx.qry.page = NULL; + ctx.repo = cgit_get_repoinfo(url); + if (ctx.repo) { + ctx.qry.repo = ctx.repo->url; return; } - cmd = strchr(url, '/'); - while (!cgit_repo && cmd) { - cmd[0] = '\0'; - cgit_repo = cgit_get_repoinfo(url); - if (cgit_repo == NULL) { - cmd[0] = '/'; - cmd = strchr(cmd + 1, '/'); - continue; + cmd = NULL; + c = strchr(url, '/'); + while (c) { + c[0] = '\0'; + repo = cgit_get_repoinfo(url); + if (repo) { + ctx.repo = repo; + cmd = c; } + c[0] = '/'; + c = strchr(c + 1, '/'); + } - cgit_query_repo = cgit_repo->url; + if (ctx.repo) { + ctx.qry.repo = ctx.repo->url; p = strchr(cmd + 1, '/'); if (p) { p[0] = '\0'; if (p[1]) - cgit_query_path = trim_end(p + 1, '/'); + ctx.qry.path = trim_end(p + 1, '/'); } - cgit_cmd = cgit_get_cmd_index(cmd + 1); - cgit_query_page = xstrdup(cmd + 1); - return; + if (cmd[1]) + ctx.qry.page = xstrdup(cmd + 1); } } -char *substr(const char *head, const char *tail) +static char *substr(const char *head, const char *tail) { char *buf; + if (tail < head) + return xstrdup(""); buf = xmalloc(tail - head + 1); strncpy(buf, head, tail - head); buf[tail - head] = '\0'; return buf; } +static void parse_user(const char *t, char **name, char **email, unsigned long *date, int *tz) +{ + struct ident_split ident; + unsigned email_len; + + if (!split_ident_line(&ident, t, strchrnul(t, '\n') - t)) { + *name = substr(ident.name_begin, ident.name_end); + + email_len = ident.mail_end - ident.mail_begin; + *email = xmalloc(strlen("<") + email_len + strlen(">") + 1); + sprintf(*email, "<%.*s>", email_len, ident.mail_begin); + + if (ident.date_begin) + *date = strtoul(ident.date_begin, NULL, 10); + if (ident.tz_begin) + *tz = atoi(ident.tz_begin); + } +} + +#ifdef NO_ICONV +#define reencode(a, b, c) +#else +static const char *reencode(char **txt, const char *src_enc, const char *dst_enc) +{ + char *tmp; + + if (!txt) + return NULL; + + if (!*txt || !src_enc || !dst_enc) + return *txt; + + /* no encoding needed if src_enc equals dst_enc */ + if (!strcasecmp(src_enc, dst_enc)) + return *txt; + + tmp = reencode_string(*txt, dst_enc, src_enc); + if (tmp) { + free(*txt); + *txt = tmp; + } + return *txt; +} +#endif + +static const char *next_header_line(const char *p) +{ + p = strchr(p, '\n'); + if (!p) + return NULL; + return p + 1; +} + +static int end_of_header(const char *p) +{ + return !p || (*p == '\n'); +} + struct commitinfo *cgit_parse_commit(struct commit *commit) { + const int sha1hex_len = 40; struct commitinfo *ret; - char *p = commit->buffer, *t = commit->buffer; + const char *p = get_cached_commit_buffer(commit, NULL); + const char *t; - ret = xmalloc(sizeof(*ret)); + ret = xcalloc(1, sizeof(struct commitinfo)); ret->commit = commit; - ret->author = NULL; - ret->author_email = NULL; - ret->committer = NULL; - ret->committer_email = NULL; - ret->subject = NULL; - ret->msg = NULL; - ret->msg_encoding = NULL; - - if (p == NULL) + + if (!p) return ret; - if (strncmp(p, "tree ", 5)) - die("Bad commit: %s", sha1_to_hex(commit->object.sha1)); - else - p += 46; // "tree " + hex[40] + "\n" - - while (!strncmp(p, "parent ", 7)) - p += 48; // "parent " + hex[40] + "\n" - - if (!strncmp(p, "author ", 7)) { - p += 7; - t = strchr(p, '<') - 1; - ret->author = substr(p, t); - p = t; - t = strchr(t, '>') + 1; - ret->author_email = substr(p, t); - ret->author_date = atol(t+1); - p = strchr(t, '\n') + 1; - } + if (!skip_prefix(p, "tree ", &p)) + die("Bad commit: %s", oid_to_hex(&commit->object.oid)); + p += sha1hex_len + 1; - if (!strncmp(p, "committer ", 9)) { - p += 9; - t = strchr(p, '<') - 1; - ret->committer = substr(p, t); - p = t; - t = strchr(t, '>') + 1; - ret->committer_email = substr(p, t); - ret->committer_date = atol(t+1); - p = strchr(t, '\n') + 1; + while (skip_prefix(p, "parent ", &p)) + p += sha1hex_len + 1; + + if (p && skip_prefix(p, "author ", &p)) { + parse_user(p, &ret->author, &ret->author_email, + &ret->author_date, &ret->author_tz); + p = next_header_line(p); } - if (!strncmp(p, "encoding ", 9)) { - p += 9; - t = strchr(p, '\n') + 1; - ret->msg_encoding = substr(p, t); - p = t; - } else - ret->msg_encoding = xstrdup(PAGE_ENCODING); - - while (*p && (*p != '\n')) - p = strchr(p, '\n') + 1; // skip unknown header fields - - while (*p == '\n') - p = strchr(p, '\n') + 1; - - t = strchr(p, '\n'); - if (t) { - if (*t == '\0') - ret->subject = "** empty **"; - else - ret->subject = substr(p, t); - p = t + 1; - - while (*p == '\n') - p = strchr(p, '\n') + 1; - ret->msg = xstrdup(p); - } else - ret->subject = substr(p, p+strlen(p)); - - if(strcmp(ret->msg_encoding, PAGE_ENCODING)) { - t = reencode_string(ret->subject, PAGE_ENCODING, - ret->msg_encoding); - if(t) { - free(ret->subject); - ret->subject = t; - } + if (p && skip_prefix(p, "committer ", &p)) { + parse_user(p, &ret->committer, &ret->committer_email, + &ret->committer_date, &ret->committer_tz); + p = next_header_line(p); + } - t = reencode_string(ret->msg, PAGE_ENCODING, - ret->msg_encoding); - if(t) { - free(ret->msg); - ret->msg = t; + if (p && skip_prefix(p, "encoding ", &p)) { + t = strchr(p, '\n'); + if (t) { + ret->msg_encoding = substr(p, t + 1); + p = t + 1; } } + if (!ret->msg_encoding) + ret->msg_encoding = xstrdup("UTF-8"); + + while (!end_of_header(p)) + p = next_header_line(p); + while (p && *p == '\n') + p++; + if (!p) + return ret; + + t = strchrnul(p, '\n'); + ret->subject = substr(p, t); + while (*t == '\n') + t++; + ret->msg = xstrdup(t); + + reencode(&ret->author, ret->msg_encoding, PAGE_ENCODING); + reencode(&ret->author_email, ret->msg_encoding, PAGE_ENCODING); + reencode(&ret->committer, ret->msg_encoding, PAGE_ENCODING); + reencode(&ret->committer_email, ret->msg_encoding, PAGE_ENCODING); + reencode(&ret->subject, ret->msg_encoding, PAGE_ENCODING); + reencode(&ret->msg, ret->msg_encoding, PAGE_ENCODING); + return ret; } - struct taginfo *cgit_parse_tag(struct tag *tag) { void *data; enum object_type type; unsigned long size; - char *p, *t; - struct taginfo *ret; + const char *p; + struct taginfo *ret = NULL; - data = read_sha1_file(tag->object.sha1, &type, &size); - if (!data || type != OBJ_TAG) { - free(data); - return 0; - } + data = read_object_file(&tag->object.oid, &type, &size); + if (!data || type != OBJ_TAG) + goto cleanup; - ret = xmalloc(sizeof(*ret)); - ret->tagger = NULL; - ret->tagger_email = NULL; - ret->tagger_date = 0; - ret->msg = NULL; - - p = data; - - while (p && *p) { - if (*p == '\n') - break; - - if (!strncmp(p, "tagger ", 7)) { - p += 7; - t = strchr(p, '<') - 1; - ret->tagger = substr(p, t); - p = t; - t = strchr(t, '>') + 1; - ret->tagger_email = substr(p, t); - ret->tagger_date = atol(t+1); + ret = xcalloc(1, sizeof(struct taginfo)); + + for (p = data; !end_of_header(p); p = next_header_line(p)) { + if (skip_prefix(p, "tagger ", &p)) { + parse_user(p, &ret->tagger, &ret->tagger_email, + &ret->tagger_date, &ret->tagger_tz); } - p = strchr(p, '\n') + 1; } - while (p && *p && (*p != '\n')) - p = strchr(p, '\n') + 1; // skip unknown tag fields + while (p && *p == '\n') + p++; - while (p && (*p == '\n')) - p = strchr(p, '\n') + 1; if (p && *p) ret->msg = xstrdup(p); + +cleanup: free(data); return ret; }