From 217ad664ab8a7a9b9a3a5a4aed2e90f88dc06b13 Mon Sep 17 00:00:00 2001 From: nobu Date: Thu, 4 Feb 2016 03:39:12 +0000 Subject: cgi/escape: Optimize CGI.escape * cgi/escape/escape.c: Optimize CGI.escape performance by C ext for ASCII-compatible encodings. [Fix GH-1238] git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@53731 b2dd03c8-39d4-4d8f-98ff-823fe69b080e --- ChangeLog | 5 +++ ext/cgi/escape/escape.c | 87 +++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 92 insertions(+) diff --git a/ChangeLog b/ChangeLog index 1b63810622..32913e76f2 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,8 @@ +Thu Feb 4 12:39:08 2016 joker1007 + + * cgi/escape/escape.c: Optimize CGI.escape performance by C ext + for ASCII-compatible encodings. [Fix GH-1238] + Thu Feb 4 11:53:56 2016 Martin Duerst * common.mk: Introduce two variables (UNICODE_DATA_DIR and diff --git a/ext/cgi/escape/escape.c b/ext/cgi/escape/escape.c index e8f64f6dcc..e04408bc61 100644 --- a/ext/cgi/escape/escape.c +++ b/ext/cgi/escape/escape.c @@ -1,6 +1,10 @@ #include "ruby.h" #include "ruby/encoding.h" +RUBY_EXTERN const char ruby_hexdigits[]; +#define lower_hexdigits (ruby_hexdigits+0) +#define upper_hexdigits (ruby_hexdigits+16) + static VALUE rb_cCGI, rb_mUtil, rb_mEscape; static void @@ -73,6 +77,68 @@ optimized_escape_html(VALUE str) } } +static int +url_unreserved_char(unsigned char c) +{ + switch (c) { + case '0': case '1': case '2': case '3': case '4': case '5': case '6': case '7': case '8': case '9': + case 'a': case 'b': case 'c': case 'd': case 'e': case 'f': case 'g': case 'h': case 'i': case 'j': + case 'k': case 'l': case 'm': case 'n': case 'o': case 'p': case 'q': case 'r': case 's': case 't': + case 'u': case 'v': case 'w': case 'x': case 'y': case 'z': + case 'A': case 'B': case 'C': case 'D': case 'E': case 'F': case 'G': case 'H': case 'I': case 'J': + case 'K': case 'L': case 'M': case 'N': case 'O': case 'P': case 'Q': case 'R': case 'S': case 'T': + case 'U': case 'V': case 'W': case 'X': case 'Y': case 'Z': + case '-': case '.': case '_': + return 1; + default: + break; + } + return 0; +} + +static VALUE +optimized_escape(VALUE str) +{ + long i, len, modified = 0, beg = 0; + VALUE dest; + const char *cstr; + char buf[4] = {'%'}; + + len = RSTRING_LEN(str); + cstr = RSTRING_PTR(str); + + for (i = 0; i < len; i++) { + if (!url_unreserved_char(cstr[i])) { + if (!modified) { + modified = 1; + dest = rb_str_buf_new(len); + } + + rb_str_cat(dest, cstr + beg, i - beg); + beg = i + 1; + + if (cstr[i] == ' ') { + rb_str_cat_cstr(dest, "+"); + } + else { + unsigned char c = (unsigned char)cstr[i]; + buf[1] = upper_hexdigits[c >> 4]; + buf[2] = upper_hexdigits[c & 0xf]; + rb_str_cat(dest, buf, 3); + } + } + } + + if (modified) { + rb_str_cat(dest, cstr + beg, len - beg); + preserve_original_state(str, dest); + return dest; + } + else { + return rb_str_dup(str); + } +} + /* * call-seq: * CGI.escapeHTML(string) -> string @@ -93,6 +159,26 @@ cgiesc_escape_html(VALUE self, VALUE str) } } +/* + * call-seq: + * CGI.escape(string) -> string + * + * Returns URL-escaped string. + * + */ +static VALUE +cgiesc_escape(VALUE self, VALUE str) +{ + StringValue(str); + + if (rb_enc_str_asciicompat_p(str)) { + return optimized_escape(str); + } + else { + return rb_call_super(1, &str); + } +} + void Init_escape(void) { @@ -100,6 +186,7 @@ Init_escape(void) rb_mEscape = rb_define_module_under(rb_cCGI, "Escape"); rb_mUtil = rb_define_module_under(rb_cCGI, "Util"); rb_define_method(rb_mEscape, "escapeHTML", cgiesc_escape_html, 1); + rb_define_method(rb_mEscape, "escape", cgiesc_escape, 1); rb_prepend_module(rb_mUtil, rb_mEscape); rb_extend_object(rb_cCGI, rb_mEscape); } -- cgit v1.2.3