golden hour
/usr/include
⬆️ Go Up
Upload
File/Folder
Size
Actions
FlexLexer.h
6.07 KB
Del
OK
GL
-
Del
OK
KF5
-
Del
OK
X11
-
Del
OK
_G_config.h
1.26 KB
Del
OK
a.out.h
4.25 KB
Del
OK
aio.h
7.27 KB
Del
OK
aliases.h
2 KB
Del
OK
alloca.h
1.19 KB
Del
OK
apache2
-
Del
OK
ar.h
1.68 KB
Del
OK
argp.h
24.75 KB
Del
OK
argz.h
6.96 KB
Del
OK
arpa
-
Del
OK
asm
-
Del
OK
asm-generic
-
Del
OK
assert.h
3.52 KB
Del
OK
autosprintf.h
2.33 KB
Del
OK
bind9
-
Del
OK
bits
-
Del
OK
bsock
-
Del
OK
byteswap.h
1.41 KB
Del
OK
c++
-
Del
OK
com_err.h
2.07 KB
Del
OK
complex.h
3.62 KB
Del
OK
cpio.h
2.21 KB
Del
OK
cpufreq.h
5.8 KB
Del
OK
criu
-
Del
OK
crypt.h
2.22 KB
Del
OK
ctype.h
11.52 KB
Del
OK
curses.h
93.19 KB
Del
OK
cursesapp.h
6.62 KB
Del
OK
cursesf.h
27.05 KB
Del
OK
cursesm.h
19.09 KB
Del
OK
cursesp.h
8.3 KB
Del
OK
cursesw.h
48.24 KB
Del
OK
cursslk.h
7.13 KB
Del
OK
db.h
120.21 KB
Del
OK
db4.7.25
-
Del
OK
db_185.h
5.84 KB
Del
OK
dbm.h
1.37 KB
Del
OK
dirent.h
12.34 KB
Del
OK
dlfcn.h
6.88 KB
Del
OK
drm
-
Del
OK
e2p
-
Del
OK
elf.h
141.01 KB
Del
OK
endian.h
2.95 KB
Del
OK
entities.h
4.56 KB
Del
OK
envz.h
2.82 KB
Del
OK
err.h
2.18 KB
Del
OK
errno.h
2.33 KB
Del
OK
error.h
2.01 KB
Del
OK
et
-
Del
OK
eti.h
2.82 KB
Del
OK
etip.h
9.04 KB
Del
OK
execinfo.h
1.5 KB
Del
OK
expat.h
41.04 KB
Del
OK
expat_external.h
3.29 KB
Del
OK
ext2fs
-
Del
OK
fcntl.h
9.89 KB
Del
OK
features.h
12.87 KB
Del
OK
fenv.h
4.5 KB
Del
OK
fmtmsg.h
3.18 KB
Del
OK
fnmatch.h
2.27 KB
Del
OK
fontconfig
-
Del
OK
form.h
17.56 KB
Del
OK
fpu_control.h
3.5 KB
Del
OK
freetype2
-
Del
OK
fstab.h
3.04 KB
Del
OK
fts.h
5.17 KB
Del
OK
ftw.h
5.15 KB
Del
OK
gconv.h
5.16 KB
Del
OK
gcrypt-module.h
7.18 KB
Del
OK
gcrypt.h
76.51 KB
Del
OK
gd.h
32.02 KB
Del
OK
gd_io.h
1.13 KB
Del
OK
gdbm
-
Del
OK
gdbm.h
5.75 KB
Del
OK
gdcache.h
2.75 KB
Del
OK
gdfontg.h
623 B
Del
OK
gdfontl.h
621 B
Del
OK
gdfontmb.h
590 B
Del
OK
gdfonts.h
585 B
Del
OK
gdfontt.h
617 B
Del
OK
gdfx.h
2.34 KB
Del
OK
gelf.h
11.05 KB
Del
OK
getopt.h
6.53 KB
Del
OK
gettext-po.h
15.17 KB
Del
OK
glob.h
6.51 KB
Del
OK
gnu
-
Del
OK
gnu-versions.h
2.29 KB
Del
OK
google
-
Del
OK
gpg-error.h
23.66 KB
Del
OK
grp.h
6.75 KB
Del
OK
gshadow.h
4.43 KB
Del
OK
gssapi
-
Del
OK
gssapi.h
181 B
Del
OK
gssrpc
-
Del
OK
iconv.h
1.83 KB
Del
OK
idn-free.h
2.41 KB
Del
OK
idn-int.h
20 B
Del
OK
idna.h
3.48 KB
Del
OK
ieee754.h
4.81 KB
Del
OK
ifaddrs.h
2.77 KB
Del
OK
inttypes.h
11.61 KB
Del
OK
jconfig.h
1.7 KB
Del
OK
jerror.h
14.4 KB
Del
OK
jmorecfg.h
13.5 KB
Del
OK
jpeglib.h
49.12 KB
Del
OK
kadm5
-
Del
OK
kdb.h
60.12 KB
Del
OK
kde4
-
Del
OK
keyutils.h
7.08 KB
Del
OK
krad.h
8.72 KB
Del
OK
krb5
-
Del
OK
krb5.h
402 B
Del
OK
langinfo.h
15.57 KB
Del
OK
lastlog.h
126 B
Del
OK
lauxlib.h
5.64 KB
Del
OK
lber.h
14.95 KB
Del
OK
lber_types.h
1.43 KB
Del
OK
ldap.h
63.46 KB
Del
OK
ldap_cdefs.h
9.24 KB
Del
OK
ldap_features.h
1.77 KB
Del
OK
ldap_schema.h
9.23 KB
Del
OK
ldap_utf8.h
3.39 KB
Del
OK
ldif.h
4.58 KB
Del
OK
libaio.h
7.8 KB
Del
OK
libdb
-
Del
OK
libelf.h
19.11 KB
Del
OK
libexslt
-
Del
OK
libgen.h
1.37 KB
Del
OK
libintl.h
4.49 KB
Del
OK
libio.h
16.87 KB
Del
OK
libltdl
-
Del
OK
libpng15
-
Del
OK
libxml2
-
Del
OK
libxslt
-
Del
OK
limits.h
4.42 KB
Del
OK
link.h
6.99 KB
Del
OK
linux
-
Del
OK
locale.h
7.78 KB
Del
OK
ltdl.h
5.58 KB
Del
OK
lua.h
11.41 KB
Del
OK
lua.hpp
191 B
Del
OK
luaconf.h
21.64 KB
Del
OK
lualib.h
1 KB
Del
OK
lzma
-
Del
OK
lzma.h
9.51 KB
Del
OK
malloc.h
6.44 KB
Del
OK
math.h
15.7 KB
Del
OK
mcheck.h
2.4 KB
Del
OK
memory.h
962 B
Del
OK
menu.h
11.67 KB
Del
OK
misc
-
Del
OK
mntent.h
3.3 KB
Del
OK
monetary.h
1.73 KB
Del
OK
mqueue.h
3.7 KB
Del
OK
mtd
-
Del
OK
mysql
-
Del
OK
nc_tparm.h
4.05 KB
Del
OK
ncurses
-
Del
OK
ncurses.h
93.19 KB
Del
OK
ncurses_dll.h
3.83 KB
Del
OK
ncursesw
-
Del
OK
ndbm.h
2.39 KB
Del
OK
net
-
Del
OK
netash
-
Del
OK
netatalk
-
Del
OK
netax25
-
Del
OK
netdb.h
27.46 KB
Del
OK
neteconet
-
Del
OK
netinet
-
Del
OK
netipx
-
Del
OK
netiucv
-
Del
OK
netpacket
-
Del
OK
netrom
-
Del
OK
netrose
-
Del
OK
nfs
-
Del
OK
nl_types.h
1.73 KB
Del
OK
nlist.h
1.56 KB
Del
OK
nss.h
1.85 KB
Del
OK
obstack.h
18.84 KB
Del
OK
openssl
-
Del
OK
panel.h
3.97 KB
Del
OK
paths.h
2.91 KB
Del
OK
pcre.h
29.73 KB
Del
OK
pcre_scanner.h
6.45 KB
Del
OK
pcre_stringpiece.h
6.11 KB
Del
OK
pcrecpp.h
25.91 KB
Del
OK
pcrecpparg.h
6.62 KB
Del
OK
pcreposix.h
5.32 KB
Del
OK
png.h
113.36 KB
Del
OK
pngconf.h
20.94 KB
Del
OK
pnglibconf.h
6.3 KB
Del
OK
poll.h
22 B
Del
OK
pr29.h
2.07 KB
Del
OK
printf.h
6.56 KB
Del
OK
profile.h
11.87 KB
Del
OK
protobuf-c
-
Del
OK
protocols
-
Del
OK
pthread.h
39.95 KB
Del
OK
pty.h
1.51 KB
Del
OK
punycode.h
9.36 KB
Del
OK
pwd.h
5.87 KB
Del
OK
python2.7
-
Del
OK
python3.6m
-
Del
OK
quota
-
Del
OK
rdma
-
Del
OK
re_comp.h
957 B
Del
OK
regex.h
21.58 KB
Del
OK
regexp.h
6.89 KB
Del
OK
resolv.h
14.67 KB
Del
OK
rpc
-
Del
OK
rpcsvc
-
Del
OK
sasl
-
Del
OK
sched.h
4.55 KB
Del
OK
scsi
-
Del
OK
search.h
5.11 KB
Del
OK
security
-
Del
OK
selinux
-
Del
OK
semaphore.h
2.36 KB
Del
OK
sepol
-
Del
OK
setjmp.h
3.97 KB
Del
OK
sgtty.h
1.33 KB
Del
OK
shadow.h
5.1 KB
Del
OK
signal.h
13.3 KB
Del
OK
slapi-plugin.h
37.45 KB
Del
OK
sound
-
Del
OK
spawn.h
6.53 KB
Del
OK
stab.h
264 B
Del
OK
stdc-predef.h
1.59 KB
Del
OK
stdint.h
7.94 KB
Del
OK
stdio.h
30.9 KB
Del
OK
stdio_ext.h
2.74 KB
Del
OK
stdlib.h
33.23 KB
Del
OK
string.h
21.75 KB
Del
OK
stringprep.h
8 KB
Del
OK
strings.h
4.55 KB
Del
OK
sys
-
Del
OK
syscall.h
25 B
Del
OK
sysexits.h
5.11 KB
Del
OK
syslog.h
24 B
Del
OK
tar.h
3.67 KB
Del
OK
tcpd.h
11.48 KB
Del
OK
term.h
38.63 KB
Del
OK
term_entry.h
7.91 KB
Del
OK
termcap.h
3.4 KB
Del
OK
termio.h
214 B
Del
OK
termios.h
3.52 KB
Del
OK
tgmath.h
18.11 KB
Del
OK
thread_db.h
15.65 KB
Del
OK
tic.h
12.35 KB
Del
OK
tiff.h
34.95 KB
Del
OK
tiffconf-64.h
3.35 KB
Del
OK
tiffconf.h
250 B
Del
OK
tiffio.h
22.52 KB
Del
OK
tiffio.hxx
1.66 KB
Del
OK
tiffvers.h
410 B
Del
OK
time.h
13.4 KB
Del
OK
tld.h
4.54 KB
Del
OK
ttyent.h
2.44 KB
Del
OK
uapi
-
Del
OK
uchar.h
2.42 KB
Del
OK
ucontext.h
1.92 KB
Del
OK
ulimit.h
1.55 KB
Del
OK
unctrl.h
3.03 KB
Del
OK
unistd.h
41.78 KB
Del
OK
ustat.h
23 B
Del
OK
utime.h
1.5 KB
Del
OK
utmp.h
3.16 KB
Del
OK
utmpx.h
4.02 KB
Del
OK
uuid
-
Del
OK
values.h
1.92 KB
Del
OK
verto-module.h
6.48 KB
Del
OK
verto.h
18.57 KB
Del
OK
video
-
Del
OK
wait.h
22 B
Del
OK
wchar.h
31.37 KB
Del
OK
wctype.h
10.89 KB
Del
OK
wordexp.h
2.47 KB
Del
OK
xcb
-
Del
OK
xen
-
Del
OK
xlocale.h
1.66 KB
Del
OK
zconf.h
14.92 KB
Del
OK
zlib.h
84.68 KB
Del
OK
Edit: pcrecpp.h
// Copyright (c) 2005, Google Inc. // All rights reserved. // // Redistribution and use in source and binary forms, with or without // modification, are permitted provided that the following conditions are // met: // // * Redistributions of source code must retain the above copyright // notice, this list of conditions and the following disclaimer. // * Redistributions in binary form must reproduce the above // copyright notice, this list of conditions and the following disclaimer // in the documentation and/or other materials provided with the // distribution. // * Neither the name of Google Inc. nor the names of its // contributors may be used to endorse or promote products derived from // this software without specific prior written permission. // // THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS // "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT // LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR // A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT // OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, // SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT // LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, // DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY // THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT // (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE // OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. // // Author: Sanjay Ghemawat // Support for PCRE_XXX modifiers added by Giuseppe Maxia, July 2005 #ifndef _PCRECPP_H #define _PCRECPP_H // C++ interface to the pcre regular-expression library. RE supports // Perl-style regular expressions (with extensions like \d, \w, \s, // ...). // // ----------------------------------------------------------------------- // REGEXP SYNTAX: // // This module is part of the pcre library and hence supports its syntax // for regular expressions. // // The syntax is pretty similar to Perl's. For those not familiar // with Perl's regular expressions, here are some examples of the most // commonly used extensions: // // "hello (\\w+) world" -- \w matches a "word" character // "version (\\d+)" -- \d matches a digit // "hello\\s+world" -- \s matches any whitespace character // "\\b(\\w+)\\b" -- \b matches empty string at a word boundary // "(?i)hello" -- (?i) turns on case-insensitive matching // "/\\*(.*?)\\*/" -- .*? matches . minimum no. of times possible // // ----------------------------------------------------------------------- // MATCHING INTERFACE: // // The "FullMatch" operation checks that supplied text matches a // supplied pattern exactly. // // Example: successful match // pcrecpp::RE re("h.*o"); // re.FullMatch("hello"); // // Example: unsuccessful match (requires full match): // pcrecpp::RE re("e"); // !re.FullMatch("hello"); // // Example: creating a temporary RE object: // pcrecpp::RE("h.*o").FullMatch("hello"); // // You can pass in a "const char*" or a "string" for "text". The // examples below tend to use a const char*. // // You can, as in the different examples above, store the RE object // explicitly in a variable or use a temporary RE object. The // examples below use one mode or the other arbitrarily. Either // could correctly be used for any of these examples. // // ----------------------------------------------------------------------- // MATCHING WITH SUB-STRING EXTRACTION: // // You can supply extra pointer arguments to extract matched subpieces. // // Example: extracts "ruby" into "s" and 1234 into "i" // int i; // string s; // pcrecpp::RE re("(\\w+):(\\d+)"); // re.FullMatch("ruby:1234", &s, &i); // // Example: does not try to extract any extra sub-patterns // re.FullMatch("ruby:1234", &s); // // Example: does not try to extract into NULL // re.FullMatch("ruby:1234", NULL, &i); // // Example: integer overflow causes failure // !re.FullMatch("ruby:1234567891234", NULL, &i); // // Example: fails because there aren't enough sub-patterns: // !pcrecpp::RE("\\w+:\\d+").FullMatch("ruby:1234", &s); // // Example: fails because string cannot be stored in integer // !pcrecpp::RE("(.*)").FullMatch("ruby", &i); // // The provided pointer arguments can be pointers to any scalar numeric // type, or one of // string (matched piece is copied to string) // StringPiece (StringPiece is mutated to point to matched piece) // T (where "bool T::ParseFrom(const char*, int)" exists) // NULL (the corresponding matched sub-pattern is not copied) // // CAVEAT: An optional sub-pattern that does not exist in the matched // string is assigned the empty string. Therefore, the following will // return false (because the empty string is not a valid number): // int number; // pcrecpp::RE::FullMatch("abc", "[a-z]+(\\d+)?", &number); // // ----------------------------------------------------------------------- // DO_MATCH // // The matching interface supports at most 16 arguments per call. // If you need more, consider using the more general interface // pcrecpp::RE::DoMatch(). See pcrecpp.h for the signature for DoMatch. // // ----------------------------------------------------------------------- // PARTIAL MATCHES // // You can use the "PartialMatch" operation when you want the pattern // to match any substring of the text. // // Example: simple search for a string: // pcrecpp::RE("ell").PartialMatch("hello"); // // Example: find first number in a string: // int number; // pcrecpp::RE re("(\\d+)"); // re.PartialMatch("x*100 + 20", &number); // assert(number == 100); // // ----------------------------------------------------------------------- // UTF-8 AND THE MATCHING INTERFACE: // // By default, pattern and text are plain text, one byte per character. // The UTF8 flag, passed to the constructor, causes both pattern // and string to be treated as UTF-8 text, still a byte stream but // potentially multiple bytes per character. In practice, the text // is likelier to be UTF-8 than the pattern, but the match returned // may depend on the UTF8 flag, so always use it when matching // UTF8 text. E.g., "." will match one byte normally but with UTF8 // set may match up to three bytes of a multi-byte character. // // Example: // pcrecpp::RE_Options options; // options.set_utf8(); // pcrecpp::RE re(utf8_pattern, options); // re.FullMatch(utf8_string); // // Example: using the convenience function UTF8(): // pcrecpp::RE re(utf8_pattern, pcrecpp::UTF8()); // re.FullMatch(utf8_string); // // NOTE: The UTF8 option is ignored if pcre was not configured with the // --enable-utf8 flag. // // ----------------------------------------------------------------------- // PASSING MODIFIERS TO THE REGULAR EXPRESSION ENGINE // // PCRE defines some modifiers to change the behavior of the regular // expression engine. // The C++ wrapper defines an auxiliary class, RE_Options, as a vehicle // to pass such modifiers to a RE class. // // Currently, the following modifiers are supported // // modifier description Perl corresponding // // PCRE_CASELESS case insensitive match /i // PCRE_MULTILINE multiple lines match /m // PCRE_DOTALL dot matches newlines /s // PCRE_DOLLAR_ENDONLY $ matches only at end N/A // PCRE_EXTRA strict escape parsing N/A // PCRE_EXTENDED ignore whitespaces /x // PCRE_UTF8 handles UTF8 chars built-in // PCRE_UNGREEDY reverses * and *? N/A // PCRE_NO_AUTO_CAPTURE disables matching parens N/A (*) // // (For a full account on how each modifier works, please check the // PCRE API reference manual). // // (*) Both Perl and PCRE allow non matching parentheses by means of the // "?:" modifier within the pattern itself. e.g. (?:ab|cd) does not // capture, while (ab|cd) does. // // For each modifier, there are two member functions whose name is made // out of the modifier in lowercase, without the "PCRE_" prefix. For // instance, PCRE_CASELESS is handled by // bool caseless(), // which returns true if the modifier is set, and // RE_Options & set_caseless(bool), // which sets or unsets the modifier. // // Moreover, PCRE_EXTRA_MATCH_LIMIT can be accessed through the // set_match_limit() and match_limit() member functions. // Setting match_limit to a non-zero value will limit the executation of // pcre to keep it from doing bad things like blowing the stack or taking // an eternity to return a result. A value of 5000 is good enough to stop // stack blowup in a 2MB thread stack. Setting match_limit to zero will // disable match limiting. Alternately, you can set match_limit_recursion() // which uses PCRE_EXTRA_MATCH_LIMIT_RECURSION to limit how much pcre // recurses. match_limit() caps the number of matches pcre does; // match_limit_recrusion() caps the depth of recursion. // // Normally, to pass one or more modifiers to a RE class, you declare // a RE_Options object, set the appropriate options, and pass this // object to a RE constructor. Example: // // RE_options opt; // opt.set_caseless(true); // // if (RE("HELLO", opt).PartialMatch("hello world")) ... // // RE_options has two constructors. The default constructor takes no // arguments and creates a set of flags that are off by default. // // The optional parameter 'option_flags' is to facilitate transfer // of legacy code from C programs. This lets you do // RE(pattern, RE_Options(PCRE_CASELESS|PCRE_MULTILINE)).PartialMatch(str); // // But new code is better off doing // RE(pattern, // RE_Options().set_caseless(true).set_multiline(true)).PartialMatch(str); // (See below) // // If you are going to pass one of the most used modifiers, there are some // convenience functions that return a RE_Options class with the // appropriate modifier already set: // CASELESS(), UTF8(), MULTILINE(), DOTALL(), EXTENDED() // // If you need to set several options at once, and you don't want to go // through the pains of declaring a RE_Options object and setting several // options, there is a parallel method that give you such ability on the // fly. You can concatenate several set_xxxxx member functions, since each // of them returns a reference to its class object. e.g.: to pass // PCRE_CASELESS, PCRE_EXTENDED, and PCRE_MULTILINE to a RE with one // statement, you may write // // RE(" ^ xyz \\s+ .* blah$", RE_Options() // .set_caseless(true) // .set_extended(true) // .set_multiline(true)).PartialMatch(sometext); // // ----------------------------------------------------------------------- // SCANNING TEXT INCREMENTALLY // // The "Consume" operation may be useful if you want to repeatedly // match regular expressions at the front of a string and skip over // them as they match. This requires use of the "StringPiece" type, // which represents a sub-range of a real string. Like RE, StringPiece // is defined in the pcrecpp namespace. // // Example: read lines of the form "var = value" from a string. // string contents = ...; // Fill string somehow // pcrecpp::StringPiece input(contents); // Wrap in a StringPiece // // string var; // int value; // pcrecpp::RE re("(\\w+) = (\\d+)\n"); // while (re.Consume(&input, &var, &value)) { // ...; // } // // Each successful call to "Consume" will set "var/value", and also // advance "input" so it points past the matched text. // // The "FindAndConsume" operation is similar to "Consume" but does not // anchor your match at the beginning of the string. For example, you // could extract all words from a string by repeatedly calling // pcrecpp::RE("(\\w+)").FindAndConsume(&input, &word) // // ----------------------------------------------------------------------- // PARSING HEX/OCTAL/C-RADIX NUMBERS // // By default, if you pass a pointer to a numeric value, the // corresponding text is interpreted as a base-10 number. You can // instead wrap the pointer with a call to one of the operators Hex(), // Octal(), or CRadix() to interpret the text in another base. The // CRadix operator interprets C-style "0" (base-8) and "0x" (base-16) // prefixes, but defaults to base-10. // // Example: // int a, b, c, d; // pcrecpp::RE re("(.*) (.*) (.*) (.*)"); // re.FullMatch("100 40 0100 0x40", // pcrecpp::Octal(&a), pcrecpp::Hex(&b), // pcrecpp::CRadix(&c), pcrecpp::CRadix(&d)); // will leave 64 in a, b, c, and d. // // ----------------------------------------------------------------------- // REPLACING PARTS OF STRINGS // // You can replace the first match of "pattern" in "str" with // "rewrite". Within "rewrite", backslash-escaped digits (\1 to \9) // can be used to insert text matching corresponding parenthesized // group from the pattern. \0 in "rewrite" refers to the entire // matching text. E.g., // // string s = "yabba dabba doo"; // pcrecpp::RE("b+").Replace("d", &s); // // will leave "s" containing "yada dabba doo". The result is true if // the pattern matches and a replacement occurs, or false otherwise. // // GlobalReplace() is like Replace(), except that it replaces all // occurrences of the pattern in the string with the rewrite. // Replacements are not subject to re-matching. E.g., // // string s = "yabba dabba doo"; // pcrecpp::RE("b+").GlobalReplace("d", &s); // // will leave "s" containing "yada dada doo". It returns the number // of replacements made. // // Extract() is like Replace(), except that if the pattern matches, // "rewrite" is copied into "out" (an additional argument) with // substitutions. The non-matching portions of "text" are ignored. // Returns true iff a match occurred and the extraction happened // successfully. If no match occurs, the string is left unaffected. #include <string> #include <pcre.h> #include <pcrecpparg.h> // defines the Arg class // This isn't technically needed here, but we include it // anyway so folks who include pcrecpp.h don't have to. #include <pcre_stringpiece.h> namespace pcrecpp { #define PCRE_SET_OR_CLEAR(b, o) \ if (b) all_options_ |= (o); else all_options_ &= ~(o); \ return *this #define PCRE_IS_SET(o) \ (all_options_ & o) == o /***** Compiling regular expressions: the RE class *****/ // RE_Options allow you to set options to be passed along to pcre, // along with other options we put on top of pcre. // Only 9 modifiers, plus match_limit and match_limit_recursion, // are supported now. class PCRECPP_EXP_DEFN RE_Options { public: // constructor RE_Options() : match_limit_(0), match_limit_recursion_(0), all_options_(0) {} // alternative constructor. // To facilitate transfer of legacy code from C programs // // This lets you do // RE(pattern, RE_Options(PCRE_CASELESS|PCRE_MULTILINE)).PartialMatch(str); // But new code is better off doing // RE(pattern, // RE_Options().set_caseless(true).set_multiline(true)).PartialMatch(str); RE_Options(int option_flags) : match_limit_(0), match_limit_recursion_(0), all_options_(option_flags) {} // we're fine with the default destructor, copy constructor, etc. // accessors and mutators int match_limit() const { return match_limit_; }; RE_Options &set_match_limit(int limit) { match_limit_ = limit; return *this; } int match_limit_recursion() const { return match_limit_recursion_; }; RE_Options &set_match_limit_recursion(int limit) { match_limit_recursion_ = limit; return *this; } bool caseless() const { return PCRE_IS_SET(PCRE_CASELESS); } RE_Options &set_caseless(bool x) { PCRE_SET_OR_CLEAR(x, PCRE_CASELESS); } bool multiline() const { return PCRE_IS_SET(PCRE_MULTILINE); } RE_Options &set_multiline(bool x) { PCRE_SET_OR_CLEAR(x, PCRE_MULTILINE); } bool dotall() const { return PCRE_IS_SET(PCRE_DOTALL); } RE_Options &set_dotall(bool x) { PCRE_SET_OR_CLEAR(x, PCRE_DOTALL); } bool extended() const { return PCRE_IS_SET(PCRE_EXTENDED); } RE_Options &set_extended(bool x) { PCRE_SET_OR_CLEAR(x, PCRE_EXTENDED); } bool dollar_endonly() const { return PCRE_IS_SET(PCRE_DOLLAR_ENDONLY); } RE_Options &set_dollar_endonly(bool x) { PCRE_SET_OR_CLEAR(x, PCRE_DOLLAR_ENDONLY); } bool extra() const { return PCRE_IS_SET(PCRE_EXTRA); } RE_Options &set_extra(bool x) { PCRE_SET_OR_CLEAR(x, PCRE_EXTRA); } bool ungreedy() const { return PCRE_IS_SET(PCRE_UNGREEDY); } RE_Options &set_ungreedy(bool x) { PCRE_SET_OR_CLEAR(x, PCRE_UNGREEDY); } bool utf8() const { return PCRE_IS_SET(PCRE_UTF8); } RE_Options &set_utf8(bool x) { PCRE_SET_OR_CLEAR(x, PCRE_UTF8); } bool no_auto_capture() const { return PCRE_IS_SET(PCRE_NO_AUTO_CAPTURE); } RE_Options &set_no_auto_capture(bool x) { PCRE_SET_OR_CLEAR(x, PCRE_NO_AUTO_CAPTURE); } RE_Options &set_all_options(int opt) { all_options_ = opt; return *this; } int all_options() const { return all_options_ ; } // TODO: add other pcre flags private: int match_limit_; int match_limit_recursion_; int all_options_; }; // These functions return some common RE_Options static inline RE_Options UTF8() { return RE_Options().set_utf8(true); } static inline RE_Options CASELESS() { return RE_Options().set_caseless(true); } static inline RE_Options MULTILINE() { return RE_Options().set_multiline(true); } static inline RE_Options DOTALL() { return RE_Options().set_dotall(true); } static inline RE_Options EXTENDED() { return RE_Options().set_extended(true); } // Interface for regular expression matching. Also corresponds to a // pre-compiled regular expression. An "RE" object is safe for // concurrent use by multiple threads. class PCRECPP_EXP_DEFN RE { public: // We provide implicit conversions from strings so that users can // pass in a string or a "const char*" wherever an "RE" is expected. RE(const string& pat) { Init(pat, NULL); } RE(const string& pat, const RE_Options& option) { Init(pat, &option); } RE(const char* pat) { Init(pat, NULL); } RE(const char* pat, const RE_Options& option) { Init(pat, &option); } RE(const unsigned char* pat) { Init(reinterpret_cast<const char*>(pat), NULL); } RE(const unsigned char* pat, const RE_Options& option) { Init(reinterpret_cast<const char*>(pat), &option); } // Copy constructor & assignment - note that these are expensive // because they recompile the expression. RE(const RE& re) { Init(re.pattern_, &re.options_); } const RE& operator=(const RE& re) { if (this != &re) { Cleanup(); // This is the code that originally came from Google // Init(re.pattern_.c_str(), &re.options_); // This is the replacement from Ari Pollak Init(re.pattern_, &re.options_); } return *this; } ~RE(); // The string specification for this RE. E.g. // RE re("ab*c?d+"); // re.pattern(); // "ab*c?d+" const string& pattern() const { return pattern_; } // If RE could not be created properly, returns an error string. // Else returns the empty string. const string& error() const { return *error_; } /***** The useful part: the matching interface *****/ // This is provided so one can do pattern.ReplaceAll() just as // easily as ReplaceAll(pattern-text, ....) bool FullMatch(const StringPiece& text, const Arg& ptr1 = no_arg, const Arg& ptr2 = no_arg, const Arg& ptr3 = no_arg, const Arg& ptr4 = no_arg, const Arg& ptr5 = no_arg, const Arg& ptr6 = no_arg, const Arg& ptr7 = no_arg, const Arg& ptr8 = no_arg, const Arg& ptr9 = no_arg, const Arg& ptr10 = no_arg, const Arg& ptr11 = no_arg, const Arg& ptr12 = no_arg, const Arg& ptr13 = no_arg, const Arg& ptr14 = no_arg, const Arg& ptr15 = no_arg, const Arg& ptr16 = no_arg) const; bool PartialMatch(const StringPiece& text, const Arg& ptr1 = no_arg, const Arg& ptr2 = no_arg, const Arg& ptr3 = no_arg, const Arg& ptr4 = no_arg, const Arg& ptr5 = no_arg, const Arg& ptr6 = no_arg, const Arg& ptr7 = no_arg, const Arg& ptr8 = no_arg, const Arg& ptr9 = no_arg, const Arg& ptr10 = no_arg, const Arg& ptr11 = no_arg, const Arg& ptr12 = no_arg, const Arg& ptr13 = no_arg, const Arg& ptr14 = no_arg, const Arg& ptr15 = no_arg, const Arg& ptr16 = no_arg) const; bool Consume(StringPiece* input, const Arg& ptr1 = no_arg, const Arg& ptr2 = no_arg, const Arg& ptr3 = no_arg, const Arg& ptr4 = no_arg, const Arg& ptr5 = no_arg, const Arg& ptr6 = no_arg, const Arg& ptr7 = no_arg, const Arg& ptr8 = no_arg, const Arg& ptr9 = no_arg, const Arg& ptr10 = no_arg, const Arg& ptr11 = no_arg, const Arg& ptr12 = no_arg, const Arg& ptr13 = no_arg, const Arg& ptr14 = no_arg, const Arg& ptr15 = no_arg, const Arg& ptr16 = no_arg) const; bool FindAndConsume(StringPiece* input, const Arg& ptr1 = no_arg, const Arg& ptr2 = no_arg, const Arg& ptr3 = no_arg, const Arg& ptr4 = no_arg, const Arg& ptr5 = no_arg, const Arg& ptr6 = no_arg, const Arg& ptr7 = no_arg, const Arg& ptr8 = no_arg, const Arg& ptr9 = no_arg, const Arg& ptr10 = no_arg, const Arg& ptr11 = no_arg, const Arg& ptr12 = no_arg, const Arg& ptr13 = no_arg, const Arg& ptr14 = no_arg, const Arg& ptr15 = no_arg, const Arg& ptr16 = no_arg) const; bool Replace(const StringPiece& rewrite, string *str) const; int GlobalReplace(const StringPiece& rewrite, string *str) const; bool Extract(const StringPiece &rewrite, const StringPiece &text, string *out) const; // Escapes all potentially meaningful regexp characters in // 'unquoted'. The returned string, used as a regular expression, // will exactly match the original string. For example, // 1.5-2.0? // may become: // 1\.5\-2\.0\? // Note QuoteMeta behaves the same as perl's QuoteMeta function, // *except* that it escapes the NUL character (\0) as backslash + 0, // rather than backslash + NUL. static string QuoteMeta(const StringPiece& unquoted); /***** Generic matching interface *****/ // Type of match (TODO: Should be restructured as part of RE_Options) enum Anchor { UNANCHORED, // No anchoring ANCHOR_START, // Anchor at start only ANCHOR_BOTH // Anchor at start and end }; // General matching routine. Stores the length of the match in // "*consumed" if successful. bool DoMatch(const StringPiece& text, Anchor anchor, int* consumed, const Arg* const* args, int n) const; // Return the number of capturing subpatterns, or -1 if the // regexp wasn't valid on construction. int NumberOfCapturingGroups() const; // The default value for an argument, to indicate the end of the argument // list. This must be used only in optional argument defaults. It should NOT // be passed explicitly. Some people have tried to use it like this: // // FullMatch(x, y, &z, no_arg, &w); // // This is a mistake, and will not work. static Arg no_arg; private: void Init(const string& pattern, const RE_Options* options); void Cleanup(); // Match against "text", filling in "vec" (up to "vecsize" * 2/3) with // pairs of integers for the beginning and end positions of matched // text. The first pair corresponds to the entire matched text; // subsequent pairs correspond, in order, to parentheses-captured // matches. Returns the number of pairs (one more than the number of // the last subpattern with a match) if matching was successful // and zero if the match failed. // I.e. for RE("(foo)|(bar)|(baz)") it will return 2, 3, and 4 when matching // against "foo", "bar", and "baz" respectively. // When matching RE("(foo)|hello") against "hello", it will return 1. // But the values for all subpattern are filled in into "vec". int TryMatch(const StringPiece& text, int startpos, Anchor anchor, bool empty_ok, int *vec, int vecsize) const; // Append the "rewrite" string, with backslash subsitutions from "text" // and "vec", to string "out". bool Rewrite(string *out, const StringPiece& rewrite, const StringPiece& text, int *vec, int veclen) const; // internal implementation for DoMatch bool DoMatchImpl(const StringPiece& text, Anchor anchor, int* consumed, const Arg* const args[], int n, int* vec, int vecsize) const; // Compile the regexp for the specified anchoring mode pcre* Compile(Anchor anchor); string pattern_; RE_Options options_; pcre* re_full_; // For full matches pcre* re_partial_; // For partial matches const string* error_; // Error indicator (or points to empty string) }; } // namespace pcrecpp #endif /* _PCRECPP_H */
Save