Convert uppercase to lowercase for tag and attribute name, fix missing is_identifier_char

2 files changed, 37 insertions, 20 deletions

diff --git a/include/HtmlParser.h b/include/HtmlParser.h
index 45dc1e1..7536777 100644
--- a/include/HtmlParser.h
+++ b/include/HtmlParser.h
@@ -9,7 +9,7 @@
 #include <stddef.h>
 
 typedef struct {
-    const char *data;
+    char *data;
     size_t size;
 } HtmlStringView;
 
@@ -28,7 +28,7 @@ typedef void (*HtmlParseCallback)(HtmlParser *html_parser, HtmlParseType parse_t
 #define UNCLOSED_TAGS_SIZE 2048
 
 struct HtmlParser {
-    const char *source;
+    char *source;
     size_t source_len;
     size_t offset;
     HtmlParseCallback parse_callback;
@@ -48,7 +48,7 @@ struct HtmlParser {
 };
 
 /* Note: HTML_PARSE_TAG_START is guaranteed to be called for a tag before HTML_PARSE_TAG_END */
-void html_parser_init(HtmlParser *self, const char *html_source, size_t len, HtmlParseCallback parse_callback, void *userdata);
+void html_parser_init(HtmlParser *self, char *html_source, size_t len, HtmlParseCallback parse_callback, void *userdata);
 void html_parser_deinit(HtmlParser *self);
 
 void html_parser_parse(HtmlParser *self);
diff --git a/src/HtmlParser.c b/src/HtmlParser.c
index 965368e..8b27d6d 100644
--- a/src/HtmlParser.c
+++ b/src/HtmlParser.c
@@ -46,7 +46,7 @@ static int is_newline(int c) {
     return c == '\n' || c == '\r';
 }
 
-static void lstrip(const char *str, size_t size, const char **output_str, size_t *output_size, int(*strip_filter_func)(int)) {
+static void lstrip(char *str, size_t size, char **output_str, size_t *output_size, int(*strip_filter_func)(int)) {
     size_t i = 0;
     while(i < size && strip_filter_func(str[i])) {
         ++i;
@@ -55,7 +55,7 @@ static void lstrip(const char *str, size_t size, const char **output_str, size_t
     *output_size = size - i;
 }
 
-static void rstrip(const char *str, size_t size, size_t *output_size, int(*strip_filter_func)(int)) {
+static void rstrip(char *str, size_t size, size_t *output_size, int(*strip_filter_func)(int)) {
     ssize_t i = size - 1;
     while(i >= 0 && strip_filter_func(str[i])) {
         --i;
@@ -63,11 +63,20 @@ static void rstrip(const char *str, size_t size, size_t *output_size, int(*strip
     *output_size = i + 1;
 }
 
-static void strip(const char *str, size_t size, const char **output_str, size_t *output_size, int(*strip_filter_func)(int)) {
+static void strip(char *str, size_t size, char **output_str, size_t *output_size, int(*strip_filter_func)(int)) {
     lstrip(str, size, output_str, output_size, strip_filter_func);
     rstrip(*output_str, *output_size, output_size, strip_filter_func);
 }
 
+static void html_string_view_to_lowercase(HtmlStringView *string_view) {
+    size_t i = 0;
+    for(; i < string_view->size; ++i) {
+        char c = string_view->data[i];
+        if(c >= 'A' && c <= 'Z')
+            string_view->data[i] += 32;
+    }
+}
+
 static int is_void_tag(HtmlStringView *tag_name) {
     HtmlStringView *tag_iter = &void_tags[0];
     /* !DOCTYPE, !--, etc.... */
@@ -98,7 +107,7 @@ static void html_parser_reset(HtmlParser *self) {
     self->unclosed_tags_offset = 0;
 }
 
-void html_parser_init(HtmlParser *self, const char *html_source, size_t len, HtmlParseCallback parse_callback, void *userdata) {
+void html_parser_init(HtmlParser *self, char *html_source, size_t len, HtmlParseCallback parse_callback, void *userdata) {
     self->source = html_source;
     self->source_len = len;
     self->parse_callback = parse_callback;
@@ -131,19 +140,7 @@ static void html_parser_advance_char(HtmlParser *self) {
         ++self->offset;
 }
 
-static int is_alpha(char c) {
-    return (c >= 'a' && c <= 'z') || (c >= 'A' && c <= 'Z');
-}
-
-static int is_digit(char c) {
-    return c >= '0' && c <= '9';
-}
-
-static int is_identifier_char(char c) {
-    return is_alpha(c) || is_digit(c) || c == '-' || c == '_' || c == '!' || c == ':';
-}
-
-static void html_parser_try_append_unclosed_tag(HtmlParser *self, const char *data, size_t size) {
+static void html_parser_try_append_unclosed_tag(HtmlParser *self, char *data, size_t size) {
     if(self->unclosed_tags_offset == UNCLOSED_TAGS_SIZE) {
         fprintf(stderr, "Reached the maximum number of unclosed tags! the html source is too broken\n");
         return;
@@ -196,6 +193,24 @@ static int is_attribute_value_char(char c) {
     }
 }
 
+static int is_identifier_char(char c) {
+    switch(c) {
+        case ' ':
+        case '\t':
+        case '\n':
+        case '\v':
+        case '"':
+        case '\'':
+        case '<':
+        case '>':
+        case '/':
+        case '=':
+            return 0;
+        default:
+            return 1;
+    }
+}
+
 /* TODO: Unescape html characters in attribute value */
 static void html_parser_parse_attribute_value_quoted(HtmlParser *self, char quote_symbol) {
     self->attribute_value.data = self->source + self->offset;
@@ -330,6 +345,7 @@ static void html_parser_parse_tag_start(HtmlParser *self) {
             if(tag_name_found) {
                 /* attribute name */
                 self->attribute_key = identifier;
+                html_string_view_to_lowercase(&self->attribute_key);
                 self->attribute_value.data = NULL;
                 self->attribute_value.size = 0;
 
@@ -351,6 +367,7 @@ static void html_parser_parse_tag_start(HtmlParser *self) {
             } else {
                 /* tag name */
                 self->tag_name = identifier;
+                html_string_view_to_lowercase(&self->tag_name);
                 tag_name_found = 1;
                 if(self->tag_name.size == 3 && memcmp(self->tag_name.data, "!--", 3) == 0) {
                     html_parser_goto_comment_end(self);