commit ed3daed30580e6c4ae62d4114c58e38b6f0f9f85
parent ada4c2ed55dd14f68430e9518f2882226a7b07cd
Author: Evgeny Grin (Karlson2k) <k2k@narod.ru>
Date: Wed, 23 Jun 2021 10:47:41 +0300
Added MHD_str_remove_tokens_caseless_() function
Diffstat:
5 files changed, 483 insertions(+), 0 deletions(-)
diff --git a/src/microhttpd/.gitignore b/src/microhttpd/.gitignore
@@ -54,6 +54,7 @@ test_http_reasons
/test_start_stop
/test_str_token
/test_str_token_remove
+/test_str_tokens_remove
test_shutdown_poll
test_shutdown_select
test_md5
diff --git a/src/microhttpd/Makefile.am b/src/microhttpd/Makefile.am
@@ -159,6 +159,7 @@ check_PROGRAMS = \
test_str_to_value \
test_str_token \
test_str_token_remove \
+ test_str_tokens_remove \
test_http_reasons \
test_md5 \
test_sha1 \
@@ -357,6 +358,9 @@ test_str_token_SOURCES = \
test_str_token_remove_SOURCES = \
test_str_token_remove.c mhd_str.c mhd_str.h mhd_assert.h mhd_options.h
+test_str_tokens_remove_SOURCES = \
+ test_str_tokens_remove.c mhd_str.c mhd_str.h mhd_assert.h mhd_options.h
+
test_http_reasons_SOURCES = \
test_http_reasons.c \
reason_phrase.c mhd_str.c mhd_str.h
diff --git a/src/microhttpd/mhd_str.c b/src/microhttpd/mhd_str.c
@@ -688,6 +688,172 @@ MHD_str_remove_token_caseless_ (const char *str,
}
+/**
+ * Perform in-place case-insensitive removal of @a tokens from the @a str.
+ *
+ * Token could be surrounded by spaces and tabs and delimited by comma.
+ * The token match succeed if substring between start, end (of string) or
+ * comma contains only case-insensitive token and optional spaces and tabs.
+ * The quoted strings and comments are not supported by this function.
+ *
+ * The input string must be normalised: empty tokens and repeated whitespaces
+ * are removed, no whitespaces before commas, exactly one space is used after
+ * each comma. The string is updated in-place.
+ *
+ * Behavior is undefined is input string in not normalised.
+ *
+ * @param[in,out] str the string to update
+ * @param[in,out] str_len the length of the @a str, not including optional
+ * terminating null-character, not null-terminated
+ * @param tokens the token to find
+ * @param tokens_len the length of @a tokens, not including optional
+ * terminating null-character.
+ * @return 'true' if any token has been removed,
+ * 'false' otherwise.
+ */
+bool
+MHD_str_remove_tokens_caseless_ (char *str,
+ size_t *str_len,
+ const char *const tokens,
+ const size_t tokens_len)
+{
+ const char *t; /**< position in the @a tokens string */
+ bool token_removed;
+
+ mhd_assert (NULL == memchr (tokens, 0, tokens_len));
+
+ token_removed = false;
+ t = tokens;
+
+ while ((size_t) (t - tokens) < tokens_len && *str_len != 0)
+ {
+ const char *tkn; /**< the current token */
+ size_t tkn_len;
+
+ /* Skip any initial whitespaces and empty tokens in 'tokens' */
+ while ( ((size_t) (t - tokens) < tokens_len) &&
+ ((' ' == *t) || ('\t' == *t) || (',' == *t)) )
+ t++;
+
+ if ((size_t) (t - tokens) >= tokens_len)
+ break; /* No more tokens, nothing to remove */
+
+ /* Found non-whitespace char which is not a comma */
+ tkn = t;
+ do
+ {
+ do
+ {
+ t++;
+ } while ((size_t) (t - tokens) < tokens_len && (' ' != *t && '\t' != *t &&
+ ',' != *t));
+ /* Found end of token string, space, tab, or comma */
+ tkn_len = t - tkn;
+
+ /* Skip all spaces and tabs */
+ while ((size_t) (t - tokens) < tokens_len && (' ' == *t || '\t' == *t))
+ t++;
+ /* Found end of token string or non-whitespace char */
+ } while((size_t) (t - tokens) < tokens_len && ',' != *t);
+
+ /* 'tkn' is the input token with 'tkn_len' chars */
+ mhd_assert (0 != tkn_len);
+
+ if (*str_len == tkn_len)
+ {
+ if (MHD_str_equal_caseless_bin_n_ (str, tkn, tkn_len))
+ {
+ *str_len = 0;
+ token_removed = true;
+ }
+ continue;
+ }
+ if (*str_len > tkn_len + 2)
+ { /* Remove 'tkn' from the input string */
+ const char *s1; /**< the "input" string / character */
+ char *s2; /**< the "output" string / character */
+
+ s1 = str;
+ s2 = str;
+
+ do
+ {
+ mhd_assert (s1 >= s2);
+ mhd_assert ((str + *str_len) >= (s1 + tkn_len));
+ if ( ( ((str + *str_len) == (s1 + tkn_len)) || (',' == s1[tkn_len]) ) &&
+ MHD_str_equal_caseless_bin_n_ (s1, tkn, tkn_len) )
+ {
+ /* current token in the input string matches the 'tkn', skip it */
+ mhd_assert ((str + *str_len == s1 + tkn_len) || \
+ (',' == s1[tkn_len]));
+ mhd_assert ((str + *str_len == s1 + tkn_len) || \
+ (' ' == s1[tkn_len + 1]));
+ token_removed = true;
+ /* Advance to the next token in the input string or beyond
+ * the end of the input string. */
+ s1 += tkn_len + 2;
+ }
+ else
+ {
+ /* current token in the input string does not match the 'tkn',
+ * copy to the output */
+ if (str != s2)
+ { /* not the first output token, add ", " to separate */
+ if (s1 != s2 + 2)
+ {
+ *(s2++) = ',';
+ *(s2++) = ' ';
+ }
+ else
+ s2 += 2;
+ }
+ do
+ {
+ if (s1 != s2)
+ *s2 = *s1;
+ s1++;
+ s2++;
+ } while (s1 < str + *str_len && ',' != *s1);
+ /* Advance to the next token in the input string or beyond
+ * the end of the input string. */
+ s1 += 2;
+ }
+ /* s1 should point to the next token in the input string or beyond
+ * the end of the input string */
+ if ((str + *str_len) < (s1 + tkn_len))
+ { /* The rest of the 's1' is too small to match 'tkn' */
+ if ((str + *str_len) > s1)
+ { /* Copy the rest of the string */
+ size_t copy_size;
+ copy_size = *str_len - (size_t) (s1 - str);
+ if (str != s2)
+ { /* not the first output token, add ", " to separate */
+ if (s1 != s2 + 2)
+ {
+ *(s2++) = ',';
+ *(s2++) = ' ';
+ }
+ else
+ s2 += 2;
+ }
+ if (s1 != s2)
+ memmove (s2, s1, copy_size);
+ s2 += copy_size;
+ }
+ *str_len = s2 - str;
+ break;
+ }
+ mhd_assert ((' ' != s1[0]) && ('\t' != s1[0]));
+ mhd_assert ((s1 == str) || (' ' == *(s1 - 1)));
+ mhd_assert ((s1 == str) || (',' == *(s1 - 2)));
+ } while (1);
+ }
+ }
+
+ return token_removed;
+}
+
+
#ifndef MHD_FAVOR_SMALL_CODE
/* Use individual function for each case */
diff --git a/src/microhttpd/mhd_str.h b/src/microhttpd/mhd_str.h
@@ -168,6 +168,36 @@ MHD_str_remove_token_caseless_ (const char *str,
ssize_t *buf_size);
+/**
+ * Perform in-place case-insensitive removal of @a tokens from the @a str.
+ *
+ * Token could be surrounded by spaces and tabs and delimited by comma.
+ * The token match succeed if substring between start, end (of string) or
+ * comma contains only case-insensitive token and optional spaces and tabs.
+ * The quoted strings and comments are not supported by this function.
+ *
+ * The input string must be normalised: empty tokens and repeated whitespaces
+ * are removed, no whitespaces before commas, exactly one space is used after
+ * each comma. The string is updated in-place.
+ *
+ * Behavior is undefined is input string in not normalised.
+ *
+ * @param[in,out] str the string to update
+ * @param[in,out] str_len the length of the @a str, not including optional
+ * terminating null-character, not null-terminated
+ * @param tokens the token to find
+ * @param tokens_len the length of @a tokens, not including optional
+ * terminating null-character.
+ * @return 'true' if any token has been removed,
+ * 'false' otherwise.
+ */
+bool
+MHD_str_remove_tokens_caseless_ (char *str,
+ size_t *str_len,
+ const char *const tokens,
+ const size_t tokens_len);
+
+
#ifndef MHD_FAVOR_SMALL_CODE
/* Use individual function for each case to improve speed */
diff --git a/src/microhttpd/test_str_tokens_remove.c b/src/microhttpd/test_str_tokens_remove.c
@@ -0,0 +1,282 @@
+/*
+ This file is part of libmicrohttpd
+ Copyright (C) 2017 Karlson2k (Evgeny Grin)
+
+ This test tool is free software; you can redistribute it and/or
+ modify it under the terms of the GNU General Public License as
+ published by the Free Software Foundation; either version 2, or
+ (at your option) any later version.
+
+ This test tool is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ Lesser General Public License for more details.
+
+ You should have received a copy of the GNU Lesser General Public
+ License along with this library; if not, write to the Free Software
+ Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
+*/
+
+/**
+ * @file microhttpd/test_str_token.c
+ * @brief Unit tests for some mhd_str functions
+ * @author Karlson2k (Evgeny Grin)
+ */
+
+#include <string.h>
+#include <stdio.h>
+#include "mhd_options.h"
+#include "mhd_str.h"
+#include "mhd_assert.h"
+
+
+static int
+expect_result_n (const char *str, size_t str_len,
+ const char *tokens, size_t tokens_len,
+ const char *expected, size_t expected_len,
+ const bool expected_removed)
+{
+ char buf_in[1024];
+ char buf_tokens[256];
+ bool res;
+ size_t result_len;
+
+ mhd_assert (sizeof(buf_in) > str_len + 2);
+ mhd_assert (sizeof(buf_tokens) > tokens_len + 2);
+
+ memset (buf_tokens, '#', sizeof(buf_tokens));
+ memcpy (buf_tokens, tokens, tokens_len); /* Copy without zero-termination */
+ memset (buf_in, '$', sizeof(buf_in));
+ memcpy (buf_in, str, str_len); /* Copy without zero-termination */
+
+ result_len = str_len;
+
+ res = MHD_str_remove_tokens_caseless_ (buf_in, &result_len,
+ buf_tokens, tokens_len);
+
+ if ( (expected_removed != res) ||
+ (expected_len != result_len) ||
+ ((0 != result_len) && (0 != memcmp (expected, buf_in, result_len))) ||
+ ('$' != buf_in[str_len]))
+ {
+ fprintf (stderr,
+ "MHD_str_remove_tokens_caseless_() FAILED:\n"
+ "\tRESULT: "
+ "\tMHD_str_remove_token_caseless_(\"%s\"->\"%.*s\", &(%lu->%lu),"
+ " \"%.*s\", %lu) returned %s\n",
+ str,
+ (int) result_len, buf_in,
+ (unsigned long) str_len, (unsigned long) result_len,
+ (int) tokens_len, buf_tokens, (unsigned long) tokens_len,
+ res ? "true" : "false");
+ fprintf (stderr,
+ "\tEXPECTED: "
+ "\tMHD_str_remove_token_caseless_(\"%s\"->\"%s\", &(%lu->%lu),"
+ " \"%.*s\", %lu) returned %s\n",
+ str,
+ expected,
+ (unsigned long) str_len, (unsigned long) expected_len,
+ (int) tokens_len, buf_tokens, (unsigned long) tokens_len,
+ expected_removed ? "true" : "false");
+ return 1;
+ }
+ return 0;
+}
+
+
+#define expect_result(s,t,e,found) \
+ expect_result_n ((s),MHD_STATICSTR_LEN_ (s), \
+ (t),MHD_STATICSTR_LEN_ (t), \
+ (e),MHD_STATICSTR_LEN_ (e), found)
+
+int
+check_result (void)
+{
+ int errcount = 0;
+ errcount += expect_result ("string", "string", "", true);
+ errcount += expect_result ("String", "string", "", true);
+ errcount += expect_result ("string", "String", "", true);
+ errcount += expect_result ("strinG", "String", "", true);
+ errcount += expect_result ("strinG", "String\t", "", true);
+ errcount += expect_result ("strinG", "\tString", "", true);
+ errcount += expect_result ("tOkEn", " \t toKEN ", "", true);
+ errcount += expect_result ("not-token, tOkEn", "token", "not-token",
+ true);
+ errcount += expect_result ("not-token, tOkEn, toke", "token",
+ "not-token, toke",
+ true);
+ errcount += expect_result ("toke, tOkEn", "token", "toke",
+ true);
+ errcount += expect_result ("not-token, tOkEn", " \t toKEN", "not-token",
+ true);
+ errcount += expect_result ("not-token, tOkEn, more-token", "toKEN\t",
+ "not-token, more-token", true);
+ errcount += expect_result ("not-token, tOkEn, more-token", "\t toKEN,,,,,",
+ "not-token, more-token", true);
+ errcount += expect_result ("a, b, c, d", ",,,,,a", "b, c, d", true);
+ errcount += expect_result ("a, b, c, d", "a,,,,,,", "b, c, d", true);
+ errcount += expect_result ("a, b, c, d", ",,,,a,,,,,,", "b, c, d", true);
+ errcount += expect_result ("a, b, c, d", "\t \t,,,,a,, , ,,,\t",
+ "b, c, d", true);
+ errcount += expect_result ("a, b, c, d", "b, c, d", "a", true);
+ errcount += expect_result ("a, b, c, d", "a, b, c, d", "", true);
+ errcount += expect_result ("a, b, c, d", "d, c, b, a", "", true);
+ errcount += expect_result ("a, b, c, d", "b, d, a, c", "", true);
+ errcount += expect_result ("a, b, c, d, e", "b, d, a, c", "e", true);
+ errcount += expect_result ("e, a, b, c, d", "b, d, a, c", "e", true);
+ errcount += expect_result ("e, a, b, c, d, e", "b, d, a, c", "e, e", true);
+ errcount += expect_result ("a, b, c, d", "b,c,d", "a", true);
+ errcount += expect_result ("a, b, c, d", "a,b,c,d", "", true);
+ errcount += expect_result ("a, b, c, d", "d,c,b,a", "", true);
+ errcount += expect_result ("a, b, c, d", "b,d,a,c", "", true);
+ errcount += expect_result ("a, b, c, d, e", "b,d,a,c", "e", true);
+ errcount += expect_result ("e, a, b, c, d", "b,d,a,c", "e", true);
+ errcount += expect_result ("e, a, b, c, d, e", "b,d,a,c", "e, e", true);
+ errcount += expect_result ("a, b, c, d", "d,,,,,,,,,c,b,a", "", true);
+ errcount += expect_result ("a, b, c, d", "b,d,a,c,,,,,,,,,,", "", true);
+ errcount += expect_result ("a, b, c, d, e", ",,,,\t,,,,b,d,a,c,\t", "e",
+ true);
+ errcount += expect_result ("e, a, b, c, d", "b,d,a,c", "e", true);
+ errcount += expect_result ("token, a, b, c, d", "token", "a, b, c, d", true);
+ errcount += expect_result ("token1, a, b, c, d", "token1", "a, b, c, d",
+ true);
+ errcount += expect_result ("token12, a, b, c, d", "token12", "a, b, c, d",
+ true);
+ errcount += expect_result ("token123, a, b, c, d", "token123", "a, b, c, d",
+ true);
+ errcount += expect_result ("token1234, a, b, c, d", "token1234", "a, b, c, d",
+ true);
+ errcount += expect_result ("token12345, a, b, c, d", "token12345",
+ "a, b, c, d", true);
+ errcount += expect_result ("token123456, a, b, c, d", "token123456",
+ "a, b, c, d", true);
+ errcount += expect_result ("token1234567, a, b, c, d", "token1234567",
+ "a, b, c, d", true);
+ errcount += expect_result ("token12345678, a, b, c, d", "token12345678",
+ "a, b, c, d", true);
+
+ errcount += expect_result ("", "a", "", false);
+ errcount += expect_result ("", "", "", false);
+ errcount += expect_result ("a, b, c, d", "bb, dd, aa, cc", "a, b, c, d",
+ false);
+ errcount += expect_result ("a, b, c, d, e", "bb, dd, aa, cc", "a, b, c, d, e",
+ false);
+ errcount += expect_result ("e, a, b, c, d", "bb, dd, aa, cc", "e, a, b, c, d",
+ false);
+ errcount += expect_result ("e, a, b, c, d, e", "bb, dd, aa, cc",
+ "e, a, b, c, d, e", false);
+ errcount += expect_result ("aa, bb, cc, dd", "b, d, a, c", "aa, bb, cc, dd",
+ false);
+ errcount += expect_result ("aa, bb, cc, dd, ee", "b, d, a, c",
+ "aa, bb, cc, dd, ee", false);
+ errcount += expect_result ("ee, aa, bb, cc, dd", "b, d, a, c",
+ "ee, aa, bb, cc, dd", false);
+ errcount += expect_result ("ee, aa, bb, cc, dd, ee", "b, d, a, c",
+ "ee, aa, bb, cc, dd, ee", false);
+
+ errcount += expect_result ("TESt", ",,,,,,test,,,,", "", true);
+ errcount += expect_result ("TESt", ",,,,,\t,test,,,,", "", true);
+ errcount += expect_result ("TESt", ",,,,,,test, ,,,", "", true);
+ errcount += expect_result ("TESt", ",,,,,, test,,,,", "", true);
+ errcount += expect_result ("TESt", ",,,,,, test-not,test,,", "",
+ true);
+ errcount += expect_result ("TESt", ",,,,,, test-not,,test,,", "",
+ true);
+ errcount += expect_result ("TESt", ",,,,,, test-not ,test,,", "",
+ true);
+ errcount += expect_result ("TESt", ",,,,,, test", "", true);
+ errcount += expect_result ("TESt", ",,,,,, test ", "", true);
+ errcount += expect_result ("TESt", "no-test,,,,,, test ", "",
+ true);
+
+ errcount += expect_result ("the-token, a, the-token, b, the-token, " \
+ "the-token, c, the-token", "the-token", "a, b, c",
+ true);
+ errcount += expect_result ("aa, the-token, bb, the-token, cc, the-token, " \
+ "the-token, dd, the-token", "the-token",
+ "aa, bb, cc, dd", true);
+ errcount += expect_result ("the-token, a, the-token, b, the-token, " \
+ "the-token, c, the-token, e", "the-token",
+ "a, b, c, e", true);
+ errcount += expect_result ("aa, the-token, bb, the-token, cc, the-token, " \
+ "the-token, dd, the-token, ee", "the-token",
+ "aa, bb, cc, dd, ee", true);
+ errcount += expect_result ("the-token, the-token, the-token, " \
+ "the-token, the-token", "the-token", "", true);
+ errcount += expect_result ("the-token, a, the-token, the-token, b, " \
+ "the-token, c, the-token, a", "c,a,b",
+ "the-token, the-token, the-token, the-token, the-token",
+ true);
+ errcount += expect_result ("the-token, xx, the-token, the-token, zz, " \
+ "the-token, yy, the-token, ww", "ww,zz,yy",
+ "the-token, xx, the-token, the-token, the-token, the-token",
+ true);
+ errcount += expect_result ("the-token, a, the-token, the-token, b, " \
+ "the-token, c, the-token, a", " c,\t a,b,,,",
+ "the-token, the-token, the-token, the-token, the-token",
+ true);
+ errcount += expect_result ("the-token, xx, the-token, the-token, zz, " \
+ "the-token, yy, the-token, ww",
+ ",,,,ww,\t zz, yy",
+ "the-token, xx, the-token, the-token, the-token, the-token",
+ true);
+ errcount += expect_result ("the-token, a, the-token, the-token, b, " \
+ "the-token, c, the-token, a", ",,,,c,\t a,b",
+ "the-token, the-token, the-token, the-token, the-token",
+ true);
+ errcount += expect_result ("the-token, xx, the-token, the-token, zz, " \
+ "the-token, yy, the-token, ww", " ww,\t zz,yy,,,,",
+ "the-token, xx, the-token, the-token, the-token, the-token",
+ true);
+ errcount += expect_result ("close, 2", "close",
+ "2", true);
+ errcount += expect_result ("close, 22", "close",
+ "22", true);
+ errcount += expect_result ("close, nothing", "close",
+ "nothing", true);
+ errcount += expect_result ("close, 2", "2",
+ "close", true);
+ errcount += expect_result ("close", "close",
+ "", true);
+ errcount += expect_result ("close, nothing", "close, token",
+ "nothing", true);
+ errcount += expect_result ("close, nothing", "nothing, token",
+ "close", true);
+ errcount += expect_result ("close, 2", "close, 10, 12, 22, nothing",
+ "2", true);
+
+ errcount += expect_result ("strin", "string", "strin", false);
+ errcount += expect_result ("Stringer", "string", "Stringer", false);
+ errcount += expect_result ("sstring", "String", "sstring", false);
+ errcount += expect_result ("string", "Strin", "string", false);
+ errcount += expect_result ("String", "\t(-strinG", "String", false);
+ errcount += expect_result ("String", ")strinG\t ", "String", false);
+ errcount += expect_result ("not-token, tOkEner", "toKEN",
+ "not-token, tOkEner", false);
+ errcount += expect_result ("not-token, tOkEns, more-token", "toKEN",
+ "not-token, tOkEns, more-token", false);
+ errcount += expect_result ("tests, quest", "TESt", "tests, quest",
+ false);
+ errcount += expect_result ("testы", "TESt", "testы", false);
+ errcount += expect_result ("test-not, хtest", "TESt",
+ "test-not, хtest", false);
+ errcount += expect_result ("testing, test not, test2", "TESt",
+ "testing, test not, test2", false);
+ errcount += expect_result ("", ",,,,,,,,,,,,,,,,,,,the-token", "", false);
+ errcount += expect_result ("a1, b1, c1, d1, e1, f1, g1", "",
+ "a1, b1, c1, d1, e1, f1, g1", false);
+
+ return errcount;
+}
+
+
+int
+main (int argc, char *argv[])
+{
+ int errcount = 0;
+ (void) argc; (void) argv; /* Unused. Silent compiler warning. */
+ errcount += check_result ();
+ if (0 == errcount)
+ printf ("All tests were passed without errors.\n");
+ return errcount == 0 ? 0 : 1;
+}
