commit 4ce4748f96abc072396d75b58d305d538c9f057a
parent 56b8135dfb2ae13dd1c53663b7c435c3edc1c910
Author: finwo <finwo@pm.me>
Date: Wed, 11 Mar 2026 23:50:25 +0100
Fix strncpy warning; auto-formatting
Diffstat:
6 files changed, 698 insertions(+), 357 deletions(-)
diff --git a/.clang-format b/.clang-format
@@ -0,0 +1,334 @@
+---
+Language: Cpp
+AccessModifierOffset: -1
+AlignAfterOpenBracket: Align
+AlignArrayOfStructures: None
+AlignConsecutiveAssignments:
+ Enabled: true
+ AcrossEmptyLines: false
+ AcrossComments: false
+ AlignCompound: false
+ AlignFunctionDeclarations: false
+ AlignFunctionPointers: false
+ PadOperators: true
+AlignConsecutiveBitFields:
+ Enabled: false
+ AcrossEmptyLines: false
+ AcrossComments: false
+ AlignCompound: false
+ AlignFunctionDeclarations: false
+ AlignFunctionPointers: false
+ PadOperators: false
+AlignConsecutiveDeclarations:
+ Enabled: true
+ AcrossEmptyLines: false
+ AcrossComments: false
+ AlignCompound: false
+ AlignFunctionDeclarations: true
+ AlignFunctionPointers: false
+ PadOperators: false
+AlignConsecutiveMacros:
+ Enabled: true
+ AcrossEmptyLines: false
+ AcrossComments: false
+ AlignCompound: false
+ AlignFunctionDeclarations: false
+ AlignFunctionPointers: false
+ PadOperators: false
+AlignConsecutiveShortCaseStatements:
+ Enabled: true
+ AcrossEmptyLines: false
+ AcrossComments: false
+ AlignCaseArrows: false
+ AlignCaseColons: false
+AlignConsecutiveTableGenBreakingDAGArgColons:
+ Enabled: false
+ AcrossEmptyLines: false
+ AcrossComments: false
+ AlignCompound: false
+ AlignFunctionDeclarations: false
+ AlignFunctionPointers: false
+ PadOperators: false
+AlignConsecutiveTableGenCondOperatorColons:
+ Enabled: false
+ AcrossEmptyLines: false
+ AcrossComments: false
+ AlignCompound: false
+ AlignFunctionDeclarations: false
+ AlignFunctionPointers: false
+ PadOperators: false
+AlignConsecutiveTableGenDefinitionColons:
+ Enabled: false
+ AcrossEmptyLines: false
+ AcrossComments: false
+ AlignCompound: false
+ AlignFunctionDeclarations: false
+ AlignFunctionPointers: false
+ PadOperators: false
+AlignEscapedNewlines: Left
+AlignOperands: Align
+AlignTrailingComments:
+ Kind: Always
+ OverEmptyLines: 0
+AllowAllArgumentsOnNextLine: true
+AllowAllParametersOfDeclarationOnNextLine: true
+AllowBreakBeforeNoexceptSpecifier: Never
+AllowShortBlocksOnASingleLine: Never
+AllowShortCaseExpressionOnASingleLine: true
+AllowShortCaseLabelsOnASingleLine: false
+AllowShortCompoundRequirementOnASingleLine: true
+AllowShortEnumsOnASingleLine: true
+AllowShortFunctionsOnASingleLine: None
+AllowShortIfStatementsOnASingleLine: WithoutElse
+AllowShortLambdasOnASingleLine: All
+AllowShortLoopsOnASingleLine: true
+AllowShortNamespacesOnASingleLine: false
+AlwaysBreakAfterDefinitionReturnType: None
+AlwaysBreakBeforeMultilineStrings: true
+AttributeMacros:
+ - __capability
+ - absl_nonnull
+ - absl_nullable
+ - absl_nullability_unknown
+BinPackArguments: true
+BinPackLongBracedList: true
+BinPackParameters: BinPack
+BitFieldColonSpacing: Both
+BracedInitializerIndentWidth: -1
+BraceWrapping:
+ AfterCaseLabel: false
+ AfterClass: false
+ AfterControlStatement: Never
+ AfterEnum: false
+ AfterExternBlock: false
+ AfterFunction: true
+ AfterNamespace: false
+ AfterObjCDeclaration: false
+ AfterStruct: false
+ AfterUnion: false
+ BeforeCatch: false
+ BeforeElse: false
+ BeforeLambdaBody: false
+ BeforeWhile: false
+ IndentBraces: false
+ SplitEmptyFunction: true
+ SplitEmptyRecord: true
+ SplitEmptyNamespace: true
+BreakAdjacentStringLiterals: true
+BreakAfterAttributes: Leave
+BreakAfterJavaFieldAnnotations: false
+BreakAfterReturnType: None
+BreakArrays: true
+BreakBeforeBinaryOperators: None
+BreakBeforeConceptDeclarations: Always
+BreakBeforeBraces: Attach
+BreakBeforeInlineASMColon: OnlyMultiline
+BreakBeforeTemplateCloser: false
+BreakBeforeTernaryOperators: true
+BreakBinaryOperations: Never
+BreakConstructorInitializers: BeforeColon
+BreakFunctionDefinitionParameters: false
+BreakInheritanceList: BeforeColon
+BreakStringLiterals: true
+BreakTemplateDeclarations: Yes
+ColumnLimit: 120
+CommentPragmas: '^ IWYU pragma:'
+CompactNamespaces: false
+ConstructorInitializerIndentWidth: 4
+ContinuationIndentWidth: 4
+Cpp11BracedListStyle: true
+DerivePointerAlignment: false
+DisableFormat: false
+EmptyLineAfterAccessModifier: Never
+EmptyLineBeforeAccessModifier: LogicalBlock
+EnumTrailingComma: Leave
+ExperimentalAutoDetectBinPacking: false
+FixNamespaceComments: true
+ForEachMacros:
+ - foreach
+ - Q_FOREACH
+ - BOOST_FOREACH
+IfMacros:
+ - KJ_IF_MAYBE
+IncludeBlocks: Regroup
+IncludeCategories:
+ - Regex: '^<ext/.*\.h>'
+ Priority: 2
+ SortPriority: 0
+ CaseSensitive: false
+ - Regex: '^<.*\.h>'
+ Priority: 1
+ SortPriority: 0
+ CaseSensitive: false
+ - Regex: '^<.*'
+ Priority: 2
+ SortPriority: 0
+ CaseSensitive: false
+ - Regex: '.*'
+ Priority: 3
+ SortPriority: 0
+ CaseSensitive: false
+IncludeIsMainRegex: '([-_](test|unittest))?$'
+IncludeIsMainSourceRegex: ''
+IndentAccessModifiers: false
+IndentCaseBlocks: true
+IndentCaseLabels: true
+IndentExportBlock: true
+IndentExternBlock: AfterExternBlock
+IndentGotoLabels: true
+IndentPPDirectives: None
+IndentRequiresClause: true
+IndentWidth: 2
+IndentWrappedFunctionNames: false
+InsertBraces: false
+InsertNewlineAtEOF: true
+InsertTrailingCommas: None
+IntegerLiteralSeparator:
+ Binary: 0
+ BinaryMinDigits: 0
+ Decimal: 0
+ DecimalMinDigits: 0
+ Hex: 0
+ HexMinDigits: 0
+JavaScriptQuotes: Leave
+JavaScriptWrapImports: true
+KeepEmptyLines:
+ AtEndOfFile: false
+ AtStartOfBlock: false
+ AtStartOfFile: false
+KeepFormFeed: false
+LambdaBodyIndentation: Signature
+LineEnding: DeriveLF
+MacroBlockBegin: ''
+MacroBlockEnd: ''
+MainIncludeChar: Quote
+MaxEmptyLinesToKeep: 1
+NamespaceIndentation: None
+ObjCBinPackProtocolList: Never
+ObjCBlockIndentWidth: 2
+ObjCBreakBeforeNestedBlockParam: true
+ObjCSpaceAfterProperty: false
+ObjCSpaceBeforeProtocolList: true
+OneLineFormatOffRegex: ''
+PackConstructorInitializers: NextLine
+PenaltyBreakAssignment: 2
+PenaltyBreakBeforeFirstCallParameter: 1
+PenaltyBreakBeforeMemberAccess: 150
+PenaltyBreakComment: 300
+PenaltyBreakFirstLessLess: 120
+PenaltyBreakOpenParenthesis: 0
+PenaltyBreakScopeResolution: 500
+PenaltyBreakString: 1000
+PenaltyBreakTemplateDeclaration: 10
+PenaltyExcessCharacter: 1000000
+PenaltyIndentedWhitespace: 0
+PenaltyReturnTypeOnItsOwnLine: 200
+PointerAlignment: Right
+PPIndentWidth: -1
+QualifierAlignment: Leave
+RawStringFormats:
+ - Language: Cpp
+ Delimiters:
+ - cc
+ - CC
+ - cpp
+ - Cpp
+ - CPP
+ - 'c++'
+ - 'C++'
+ CanonicalDelimiter: ''
+ BasedOnStyle: google
+ - Language: TextProto
+ Delimiters:
+ - pb
+ - PB
+ - proto
+ - PROTO
+ EnclosingFunctions:
+ - EqualsProto
+ - EquivToProto
+ - PARSE_PARTIAL_TEXT_PROTO
+ - PARSE_TEST_PROTO
+ - PARSE_TEXT_PROTO
+ - ParseTextOrDie
+ - ParseTextProtoOrDie
+ - ParseTestProto
+ - ParsePartialTestProto
+ CanonicalDelimiter: pb
+ BasedOnStyle: google
+ReferenceAlignment: Pointer
+ReflowComments: Always
+RemoveBracesLLVM: false
+RemoveEmptyLinesInUnwrappedLines: false
+RemoveParentheses: Leave
+RemoveSemicolon: false
+RequiresClausePosition: OwnLine
+RequiresExpressionIndentation: OuterScope
+SeparateDefinitionBlocks: Leave
+ShortNamespaceLines: 1
+SkipMacroDefinitionBody: false
+SortIncludes:
+ Enabled: true
+ IgnoreCase: false
+SortJavaStaticImport: Before
+SortUsingDeclarations: LexicographicNumeric
+SpaceAfterCStyleCast: false
+SpaceAfterLogicalNot: false
+SpaceAfterOperatorKeyword: false
+SpaceAfterTemplateKeyword: true
+SpaceAroundPointerQualifiers: Default
+SpaceBeforeAssignmentOperators: true
+SpaceBeforeCaseColon: false
+SpaceBeforeCpp11BracedList: false
+SpaceBeforeCtorInitializerColon: true
+SpaceBeforeInheritanceColon: true
+SpaceBeforeJsonColon: false
+SpaceBeforeParens: ControlStatements
+SpaceBeforeParensOptions:
+ AfterControlStatements: true
+ AfterForeachMacros: true
+ AfterFunctionDefinitionName: false
+ AfterFunctionDeclarationName: false
+ AfterIfMacros: true
+ AfterNot: false
+ AfterOverloadedOperator: false
+ AfterPlacementOperator: true
+ AfterRequiresInClause: false
+ AfterRequiresInExpression: false
+ BeforeNonEmptyParentheses: false
+SpaceBeforeRangeBasedForLoopColon: true
+SpaceBeforeSquareBrackets: false
+SpaceInEmptyBlock: false
+SpacesBeforeTrailingComments: 2
+SpacesInAngles: Never
+SpacesInContainerLiterals: true
+SpacesInLineCommentPrefix:
+ Minimum: 1
+ Maximum: -1
+SpacesInParens: Never
+SpacesInParensOptions:
+ ExceptDoubleParentheses: false
+ InCStyleCasts: false
+ InConditionalStatements: false
+ InEmptyParentheses: false
+ Other: false
+SpacesInSquareBrackets: false
+Standard: Auto
+StatementAttributeLikeMacros:
+ - Q_EMIT
+StatementMacros:
+ - Q_UNUSED
+ - QT_REQUIRE_VERSION
+TableGenBreakInsideDAGArg: DontBreak
+TabWidth: 8
+UseTab: Never
+VerilogBreakBetweenInstancePorts: true
+WhitespaceSensitiveMacros:
+ - BOOST_PP_STRINGIZE
+ - CF_SWIFT_NAME
+ - NS_SWIFT_NAME
+ - PP_STRINGIZE
+ - STRINGIZE
+WrapNamespaceBodyWithEmptyLines: Leave
+...
+
diff --git a/.gitignore b/.gitignore
@@ -1,6 +1,7 @@
/test/unix-socket
/test/empty-host
/test/basic
+/test/length-limits
*.o
.DS_Store
._.DS_Store
diff --git a/Makefile b/Makefile
@@ -0,0 +1,9 @@
+FIND=$(shell which gfind find | head -1)
+
+.PHONY: test
+test:
+ @$(MAKE) -C test run
+
+.PHONY: format
+format:
+ $(FIND) src/ -type f \( -name '*.c' -o -name '*.h' \) -exec clang-format -i {} +
diff --git a/src/url-parser.c b/src/url-parser.c
@@ -37,19 +37,22 @@
#include "url-parser.h"
+#include <ctype.h>
+#include <limits.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
-#include <ctype.h>
-#include <limits.h>
static const char *_last_error = NULL;
const char *parse_url_last_error(void) {
- return _last_error;
+ return _last_error;
}
-#define SET_ERROR(msg) do { _last_error = (msg); } while(0)
+#define SET_ERROR(msg) \
+ do { \
+ _last_error = (msg); \
+ } while (0)
/*
* Prototype declarations
@@ -59,401 +62,395 @@ static __inline__ int _is_scheme_char(int);
/*
* Check if scheme is a path-based scheme (unix socket, file path, etc.)
*/
-static __inline__ int
-_is_path_scheme(const char *scheme)
-{
- if ( NULL == scheme ) {
- return 0;
- }
- if ( 0 == strncmp(scheme, "unix", 4) && scheme[4] == '\0' ) {
- return 1;
- }
- if ( 0 == strncmp(scheme, "file", 4) && scheme[4] == '\0' ) {
- return 1;
- }
- if ( 0 == strncmp(scheme, "cunix", 5) && scheme[5] == '\0' ) {
- return 1;
- }
+static __inline__ int _is_path_scheme(const char *scheme) {
+ if (NULL == scheme) {
return 0;
+ }
+ if (0 == strncmp(scheme, "unix", 4) && scheme[4] == '\0') {
+ return 1;
+ }
+ if (0 == strncmp(scheme, "file", 4) && scheme[4] == '\0') {
+ return 1;
+ }
+ if (0 == strncmp(scheme, "cunix", 5) && scheme[5] == '\0') {
+ return 1;
+ }
+ return 0;
}
/*
* Check whether the character is permitted in scheme string
*/
-static __inline__ int
-_is_scheme_char(int c)
-{
- return (!isalpha(c) && '+' != c && '-' != c && '.' != c) ? 0 : 1;
+static __inline__ int _is_scheme_char(int c) {
+ return (!isalpha(c) && '+' != c && '-' != c && '.' != c) ? 0 : 1;
}
/*
* See RFC 1738, 3986
*/
-struct parsed_url *
-parse_url(const char *url)
-{
- struct parsed_url *purl;
- const char *tmpstr;
- const char *curstr;
- size_t len;
- size_t i;
- int bracket_flag;
- int is_path;
+struct parsed_url *parse_url(const char *url) {
+ struct parsed_url *purl;
+ const char *tmpstr;
+ const char *curstr;
+ size_t len;
+ size_t i;
+ int bracket_flag;
+ int is_path;
- /* Allocate the parsed url storage */
- purl = malloc(sizeof(struct parsed_url));
- if ( NULL == purl ) {
- return NULL;
+ /* Allocate the parsed url storage */
+ purl = malloc(sizeof(struct parsed_url));
+ if (NULL == purl) {
+ return NULL;
+ }
+ purl->scheme = NULL;
+ purl->host = NULL;
+ purl->port = NULL;
+ purl->path = NULL;
+ purl->query = NULL;
+ purl->fragment = NULL;
+ purl->username = NULL;
+ purl->password = NULL;
+
+ curstr = url;
+
+ /*
+ * <scheme>:<scheme-specific-part>
+ * <scheme> := [a-z\+\-\.]+
+ * upper case = lower case for resiliency
+ */
+ /* Read scheme */
+ tmpstr = strchr(curstr, ':');
+ if (NULL == tmpstr) {
+ parsed_url_free(purl);
+ return NULL;
+ }
+ /* Get the scheme length */
+ len = tmpstr - curstr;
+ if (len > 64) {
+ SET_ERROR("ERR_SCHEME_TOO_LONG");
+ parsed_url_free(purl);
+ return NULL;
+ }
+ /* Check restrictions */
+ for (i = 0; i < len; i++) {
+ if (!_is_scheme_char(curstr[i])) {
+ parsed_url_free(purl);
+ return NULL;
}
- purl->scheme = NULL;
- purl->host = NULL;
- purl->port = NULL;
- purl->path = NULL;
- purl->query = NULL;
- purl->fragment = NULL;
- purl->username = NULL;
- purl->password = NULL;
+ }
+ /* Copy the scheme to the storage */
+ purl->scheme = malloc(sizeof(char) * (len + 1));
+ if (NULL == purl->scheme) {
+ parsed_url_free(purl);
+ return NULL;
+ }
+ if (len > 0) {
+ (void)strncpy(purl->scheme, curstr, len);
+ }
+ purl->scheme[len] = '\0';
+ /* Make the character to lower if it is upper case. */
+ for (i = 0; i < len; i++) {
+ purl->scheme[i] = tolower(purl->scheme[i]);
+ }
- curstr = url;
+ /* Check if this is a path-based scheme */
+ is_path = _is_path_scheme(purl->scheme);
- /*
- * <scheme>:<scheme-specific-part>
- * <scheme> := [a-z\+\-\.]+
- * upper case = lower case for resiliency
- */
- /* Read scheme */
- tmpstr = strchr(curstr, ':');
- if ( NULL == tmpstr ) {
- parsed_url_free(purl);
- return NULL;
+ /* Skip ':' */
+ tmpstr++;
+ curstr = tmpstr;
+
+ /*
+ * Normalize: ensure we have // after scheme
+ * If missing, treat everything as path
+ */
+ if ('/' != curstr[0] || '/' != curstr[1]) {
+ /* No // - entire rest is path */
+ tmpstr = curstr;
+ while ('\0' != *tmpstr) {
+ tmpstr++;
}
- /* Get the scheme length */
len = tmpstr - curstr;
- if ( len > 64 ) {
- SET_ERROR("ERR_SCHEME_TOO_LONG");
- parsed_url_free(purl);
- return NULL;
- }
- /* Check restrictions */
- for ( i = 0; i < len; i++ ) {
- if ( !_is_scheme_char(curstr[i]) ) {
- parsed_url_free(purl);
- return NULL;
- }
- }
- /* Copy the scheme to the storage */
- purl->scheme = malloc(sizeof(char) * (len + 1));
- if ( NULL == purl->scheme ) {
+ if (len > 0) {
+ purl->path = malloc(sizeof(char) * (len + 1));
+ if (NULL == purl->path) {
parsed_url_free(purl);
return NULL;
+ }
+ (void)strncpy(purl->path, curstr, len);
+ purl->path[len] = '\0';
}
- (void)strncpy(purl->scheme, curstr, len);
- purl->scheme[len] = '\0';
- /* Make the character to lower if it is upper case. */
- for ( i = 0; i < len; i++ ) {
- purl->scheme[i] = tolower(purl->scheme[i]);
- }
+ return purl;
+ }
- /* Check if this is a path-based scheme */
- is_path = _is_path_scheme(purl->scheme);
+ /* Skip the "//" */
+ curstr += 2;
- /* Skip ':' */
+ /*
+ * Detect and consume username:password, consume @
+ */
+ tmpstr = curstr;
+ while ('\0' != *tmpstr && '@' != *tmpstr) {
tmpstr++;
- curstr = tmpstr;
+ }
- /*
- * Normalize: ensure we have // after scheme
- * If missing, treat everything as path
- */
- if ( '/' != curstr[0] || '/' != curstr[1] ) {
- /* No // - entire rest is path */
- tmpstr = curstr;
- while ( '\0' != *tmpstr ) {
- tmpstr++;
- }
- len = tmpstr - curstr;
- if ( len > 0 ) {
- purl->path = malloc(sizeof(char) * (len + 1));
- if ( NULL == purl->path ) {
- parsed_url_free(purl);
- return NULL;
- }
- (void)strncpy(purl->path, curstr, len);
- purl->path[len] = '\0';
- }
- return purl;
+ if ('@' == *tmpstr) {
+ /* Has userinfo */
+ /* First check if there's a password (look for : before @) */
+ const char *colon = curstr;
+ int has_password = 0;
+ while (colon < tmpstr) {
+ if (':' == *colon) {
+ has_password = 1;
+ break;
+ }
+ colon++;
}
- /* Skip the "//" */
- curstr += 2;
-
- /*
- * Detect and consume username:password, consume @
- */
- tmpstr = curstr;
- while ( '\0' != *tmpstr && '@' != *tmpstr ) {
- tmpstr++;
+ /* Read username */
+ const char *username_start = curstr;
+ if (has_password) {
+ len = colon - curstr;
+ } else {
+ len = tmpstr - curstr;
+ }
+ if (len > 255) {
+ SET_ERROR("ERR_USERNAME_TOO_LONG");
+ parsed_url_free(purl);
+ return NULL;
+ }
+ if (len > 0) {
+ purl->username = malloc(sizeof(char) * (len + 1));
+ if (NULL == purl->username) {
+ parsed_url_free(purl);
+ return NULL;
+ }
+ (void)strncpy(purl->username, username_start, len);
+ purl->username[len] = '\0';
}
- if ( '@' == *tmpstr ) {
- /* Has userinfo */
- /* First check if there's a password (look for : before @) */
- const char *colon = curstr;
- int has_password = 0;
- while (colon < tmpstr) {
- if (':' == *colon) {
- has_password = 1;
- break;
- }
- colon++;
- }
-
- /* Read username */
- const char *username_start = curstr;
- if (has_password) {
- len = colon - curstr;
- } else {
- len = tmpstr - curstr;
- }
- if ( len > 255 ) {
- SET_ERROR("ERR_USERNAME_TOO_LONG");
- parsed_url_free(purl);
- return NULL;
- }
- if ( len > 0 ) {
- purl->username = malloc(sizeof(char) * (len + 1));
- if ( NULL == purl->username ) {
- parsed_url_free(purl);
- return NULL;
- }
- (void)strncpy(purl->username, username_start, len);
- purl->username[len] = '\0';
+ /* Skip to password or @ */
+ if (has_password) {
+ curstr = colon + 1;
+ /* Read password */
+ tmpstr = curstr;
+ while ('\0' != *tmpstr && '@' != *tmpstr) {
+ tmpstr++;
+ }
+ len = tmpstr - curstr;
+ if (len > 255) {
+ SET_ERROR("ERR_PASSWORD_TOO_LONG");
+ parsed_url_free(purl);
+ return NULL;
+ }
+ if (len > 0) {
+ purl->password = malloc(sizeof(char) * (len + 1));
+ if (NULL == purl->password) {
+ parsed_url_free(purl);
+ return NULL;
}
+ (void)strncpy(purl->password, curstr, len);
+ purl->password[len] = '\0';
+ }
+ curstr = tmpstr;
+ } else {
+ /* No password - advance past username to @ */
+ curstr = username_start + len;
+ }
+ /* Skip @ */
+ while ('@' == *curstr) {
+ curstr++;
+ }
+ }
- /* Skip to password or @ */
- if (has_password) {
- curstr = colon + 1;
- /* Read password */
- tmpstr = curstr;
- while ( '\0' != *tmpstr && '@' != *tmpstr ) {
- tmpstr++;
- }
- len = tmpstr - curstr;
- if ( len > 255 ) {
- SET_ERROR("ERR_PASSWORD_TOO_LONG");
- parsed_url_free(purl);
- return NULL;
- }
- if ( len > 0 ) {
- purl->password = malloc(sizeof(char) * (len + 1));
- if ( NULL == purl->password ) {
- parsed_url_free(purl);
- return NULL;
- }
- (void)strncpy(purl->password, curstr, len);
- purl->password[len] = '\0';
- }
- curstr = tmpstr;
- } else {
- /* No password - advance past username to @ */
- curstr = username_start + len;
- }
- /* Skip @ */
- while ( '@' == *curstr ) {
- curstr++;
- }
+ /*
+ * If NOT a path scheme, detect and consume host:port
+ */
+ if (!is_path) {
+ if ('[' == *curstr) {
+ bracket_flag = 1;
+ curstr++;
+ } else {
+ bracket_flag = 0;
}
- /*
- * If NOT a path scheme, detect and consume host:port
- */
- if ( !is_path ) {
- if ( '[' == *curstr ) {
- bracket_flag = 1;
- curstr++;
- } else {
- bracket_flag = 0;
- }
+ /* Read host */
+ tmpstr = curstr;
+ while ('\0' != *tmpstr) {
+ if (bracket_flag && ']' == *tmpstr) {
+ break;
+ } else if (!bracket_flag && (':' == *tmpstr || '/' == *tmpstr || '?' == *tmpstr || '#' == *tmpstr)) {
+ break;
+ }
+ tmpstr++;
+ }
+ len = tmpstr - curstr;
+ if (len > 255) {
+ SET_ERROR("ERR_HOST_TOO_LONG");
+ parsed_url_free(purl);
+ return NULL;
+ }
- /* Read host */
- tmpstr = curstr;
- while ( '\0' != *tmpstr ) {
- if ( bracket_flag && ']' == *tmpstr ) {
- break;
- } else if ( !bracket_flag && (':' == *tmpstr || '/' == *tmpstr || '?' == *tmpstr || '#' == *tmpstr) ) {
- break;
- }
- tmpstr++;
- }
- len = tmpstr - curstr;
- if ( len > 255 ) {
- SET_ERROR("ERR_HOST_TOO_LONG");
- parsed_url_free(purl);
- return NULL;
- }
+ if (len > 0) {
+ purl->host = malloc(sizeof(char) * (len + 1));
+ if (NULL == purl->host) {
+ parsed_url_free(purl);
+ return NULL;
+ }
+ (void)strncpy(purl->host, curstr, len);
+ purl->host[len] = '\0';
+ }
+ curstr = tmpstr;
- if ( len > 0 ) {
- purl->host = malloc(sizeof(char) * (len + 1));
- if ( NULL == purl->host ) {
- parsed_url_free(purl);
- return NULL;
- }
- (void)strncpy(purl->host, curstr, len);
- purl->host[len] = '\0';
- }
- curstr = tmpstr;
+ /* Skip ']' if IPv6 */
+ if (']' == *curstr) {
+ curstr++;
+ }
- /* Skip ']' if IPv6 */
- if ( ']' == *curstr ) {
- curstr++;
+ /* Read port */
+ if (':' == *curstr) {
+ curstr++;
+ tmpstr = curstr;
+ while ('\0' != *tmpstr && '/' != *tmpstr && '?' != *tmpstr && '#' != *tmpstr) {
+ tmpstr++;
+ }
+ len = tmpstr - curstr;
+ if (len > 5) {
+ SET_ERROR("ERR_PORT_TOO_LONG");
+ parsed_url_free(purl);
+ return NULL;
+ }
+ if (len > 0) {
+ char port_str[6];
+ size_t copy_len = len < 5 ? len : 5;
+ (void)strncpy(port_str, curstr, copy_len);
+ port_str[copy_len] = '\0';
+ long port_val = strtol(port_str, NULL, 10);
+ if (port_val < 1 || port_val > 65535) {
+ SET_ERROR("ERR_PORT_INVALID");
+ parsed_url_free(purl);
+ return NULL;
}
-
- /* Read port */
- if ( ':' == *curstr ) {
- curstr++;
- tmpstr = curstr;
- while ( '\0' != *tmpstr && '/' != *tmpstr && '?' != *tmpstr && '#' != *tmpstr ) {
- tmpstr++;
- }
- len = tmpstr - curstr;
- if ( len > 5 ) {
- SET_ERROR("ERR_PORT_TOO_LONG");
- parsed_url_free(purl);
- return NULL;
- }
- if ( len > 0 ) {
- char port_str[6];
- size_t copy_len = len < 5 ? len : 5;
- (void)strncpy(port_str, curstr, copy_len);
- port_str[copy_len] = '\0';
- long port_val = strtol(port_str, NULL, 10);
- if ( port_val < 1 || port_val > 65535 ) {
- SET_ERROR("ERR_PORT_INVALID");
- parsed_url_free(purl);
- return NULL;
- }
- purl->port = malloc(sizeof(char) * (len + 1));
- if ( NULL == purl->port ) {
- parsed_url_free(purl);
- return NULL;
- }
- (void)strncpy(purl->port, curstr, len);
- purl->port[len] = '\0';
- }
- curstr = tmpstr;
+ purl->port = malloc(sizeof(char) * (len + 1));
+ if (NULL == purl->port) {
+ parsed_url_free(purl);
+ return NULL;
}
+ (void)strncpy(purl->port, curstr, len);
+ purl->port[len] = '\0';
+ }
+ curstr = tmpstr;
}
+ }
+
+ /* End of string? */
+ if ('\0' == *curstr) {
+ return purl;
+ }
- /* End of string? */
- if ( '\0' == *curstr ) {
- return purl;
+ /* Parse path */
+ tmpstr = curstr;
+ while ('\0' != *tmpstr && '?' != *tmpstr && '#' != *tmpstr) {
+ tmpstr++;
+ }
+ len = tmpstr - curstr;
+ if (len > 4096) {
+ SET_ERROR("ERR_PATH_TOO_LONG");
+ parsed_url_free(purl);
+ return NULL;
+ }
+ if (len > 0) {
+ purl->path = malloc(sizeof(char) * (len + 1));
+ if (NULL == purl->path) {
+ parsed_url_free(purl);
+ return NULL;
}
+ (void)strncpy(purl->path, curstr, len);
+ purl->path[len] = '\0';
+ }
+ curstr = tmpstr;
- /* Parse path */
+ /* Parse query */
+ if ('?' == *curstr) {
+ curstr++;
tmpstr = curstr;
- while ( '\0' != *tmpstr && '?' != *tmpstr && '#' != *tmpstr ) {
- tmpstr++;
+ while ('\0' != *tmpstr && '#' != *tmpstr) {
+ tmpstr++;
}
len = tmpstr - curstr;
- if ( len > 4096 ) {
- SET_ERROR("ERR_PATH_TOO_LONG");
+ if (len > 4096) {
+ SET_ERROR("ERR_QUERY_TOO_LONG");
+ parsed_url_free(purl);
+ return NULL;
+ }
+ if (len > 0) {
+ purl->query = malloc(sizeof(char) * (len + 1));
+ if (NULL == purl->query) {
parsed_url_free(purl);
return NULL;
- }
- if ( len > 0 ) {
- purl->path = malloc(sizeof(char) * (len + 1));
- if ( NULL == purl->path ) {
- parsed_url_free(purl);
- return NULL;
- }
- (void)strncpy(purl->path, curstr, len);
- purl->path[len] = '\0';
+ }
+ (void)strncpy(purl->query, curstr, len);
+ purl->query[len] = '\0';
}
curstr = tmpstr;
+ }
- /* Parse query */
- if ( '?' == *curstr ) {
- curstr++;
- tmpstr = curstr;
- while ( '\0' != *tmpstr && '#' != *tmpstr ) {
- tmpstr++;
- }
- len = tmpstr - curstr;
- if ( len > 4096 ) {
- SET_ERROR("ERR_QUERY_TOO_LONG");
- parsed_url_free(purl);
- return NULL;
- }
- if ( len > 0 ) {
- purl->query = malloc(sizeof(char) * (len + 1));
- if ( NULL == purl->query ) {
- parsed_url_free(purl);
- return NULL;
- }
- (void)strncpy(purl->query, curstr, len);
- purl->query[len] = '\0';
- }
- curstr = tmpstr;
+ /* Parse fragment */
+ if ('#' == *curstr) {
+ curstr++;
+ tmpstr = curstr;
+ while ('\0' != *tmpstr) {
+ tmpstr++;
}
-
- /* Parse fragment */
- if ( '#' == *curstr ) {
- curstr++;
- tmpstr = curstr;
- while ( '\0' != *tmpstr ) {
- tmpstr++;
- }
- len = tmpstr - curstr;
- if ( len > 4096 ) {
- SET_ERROR("ERR_FRAGMENT_TOO_LONG");
- parsed_url_free(purl);
- return NULL;
- }
- if ( len > 0 ) {
- purl->fragment = malloc(sizeof(char) * (len + 1));
- if ( NULL == purl->fragment ) {
- parsed_url_free(purl);
- return NULL;
- }
- (void)strncpy(purl->fragment, curstr, len);
- purl->fragment[len] = '\0';
- }
+ len = tmpstr - curstr;
+ if (len > 4096) {
+ SET_ERROR("ERR_FRAGMENT_TOO_LONG");
+ parsed_url_free(purl);
+ return NULL;
+ }
+ if (len > 0) {
+ purl->fragment = malloc(sizeof(char) * (len + 1));
+ if (NULL == purl->fragment) {
+ parsed_url_free(purl);
+ return NULL;
+ }
+ (void)strncpy(purl->fragment, curstr, len);
+ purl->fragment[len] = '\0';
}
+ }
- return purl;
+ return purl;
}
/*
* Free memory of parsed url
*/
-void
-parsed_url_free(struct parsed_url *purl)
-{
- if ( NULL != purl ) {
- if ( NULL != purl->scheme ) {
- free(purl->scheme);
- }
- if ( NULL != purl->host ) {
- free(purl->host);
- }
- if ( NULL != purl->port ) {
- free(purl->port);
- }
- if ( NULL != purl->path ) {
- free(purl->path);
- }
- if ( NULL != purl->query ) {
- free(purl->query);
- }
- if ( NULL != purl->fragment ) {
- free(purl->fragment);
- }
- if ( NULL != purl->username ) {
- free(purl->username);
- }
- if ( NULL != purl->password ) {
- free(purl->password);
- }
- free(purl);
+void parsed_url_free(struct parsed_url *purl) {
+ if (NULL != purl) {
+ if (NULL != purl->scheme) {
+ free(purl->scheme);
+ }
+ if (NULL != purl->host) {
+ free(purl->host);
+ }
+ if (NULL != purl->port) {
+ free(purl->port);
+ }
+ if (NULL != purl->path) {
+ free(purl->path);
+ }
+ if (NULL != purl->query) {
+ free(purl->query);
+ }
+ if (NULL != purl->fragment) {
+ free(purl->fragment);
+ }
+ if (NULL != purl->username) {
+ free(purl->username);
+ }
+ if (NULL != purl->password) {
+ free(purl->password);
}
+ free(purl);
+ }
}
diff --git a/src/url-parser.h b/src/url-parser.h
@@ -42,26 +42,26 @@
* URL storage
*/
struct parsed_url {
- char *scheme; /* mandatory */
- char *host; /* mandatory */
- char *port; /* optional */
- char *path; /* optional */
- char *query; /* optional */
- char *fragment; /* optional */
- char *username; /* optional */
- char *password; /* optional */
+ char *scheme; /* mandatory */
+ char *host; /* mandatory */
+ char *port; /* optional */
+ char *path; /* optional */
+ char *query; /* optional */
+ char *fragment; /* optional */
+ char *username; /* optional */
+ char *password; /* optional */
};
#ifdef __cplusplus
extern "C" {
#endif
- /*
- * Declaration of function prototypes
- */
- struct parsed_url * parse_url(const char *);
- void parsed_url_free(struct parsed_url *);
- const char *parse_url_last_error(void);
+/*
+ * Declaration of function prototypes
+ */
+struct parsed_url *parse_url(const char *);
+void parsed_url_free(struct parsed_url *);
+const char *parse_url_last_error(void);
#ifdef __cplusplus
}
diff --git a/test/length-limits b/test/length-limits
Binary files differ.
