Sync lexbor with master on PHP 8.4

Author: ndossche

ext/dom/config.m4

@@ -56,15 +56,10 @@ if test "$PHP_DOM" != "no"; then
       $LEXBOR_DIR/dom/interfaces/processing_instruction.c
       $LEXBOR_DIR/dom/interfaces/shadow_root.c
       $LEXBOR_DIR/dom/interfaces/text.c
-      $LEXBOR_DIR/encoding/big5.c
       $LEXBOR_DIR/encoding/decode.c
       $LEXBOR_DIR/encoding/encode.c
       $LEXBOR_DIR/encoding/encoding.c
-      $LEXBOR_DIR/encoding/euc_kr.c
-      $LEXBOR_DIR/encoding/gb18030.c
-      $LEXBOR_DIR/encoding/iso_2022_jp_katakana.c
-      $LEXBOR_DIR/encoding/jis0208.c
-      $LEXBOR_DIR/encoding/jis0212.c
+      $LEXBOR_DIR/encoding/multi.c
       $LEXBOR_DIR/encoding/range.c
       $LEXBOR_DIR/encoding/res.c
       $LEXBOR_DIR/encoding/single.c

ext/dom/config.w32

@@ -27,7 +27,7 @@ if (PHP_DOM == "yes") {
 		ADD_SOURCES("ext/dom/lexbor/lexbor/html/tree", "active_formatting.c open_elements.c error.c", "dom");
 		ADD_SOURCES("ext/dom/lexbor/lexbor/html/tree/insertion_mode", "after_after_body.c after_after_frameset.c after_body.c after_frameset.c after_head.c before_head.c before_html.c foreign_content.c in_body.c in_caption.c in_cell.c in_column_group.c in_frameset.c in_head.c in_head_noscript.c initial.c in_row.c in_select.c in_select_in_table.c in_table_body.c in_table.c in_table_text.c in_template.c text.c", "dom");
 		ADD_SOURCES("ext/dom/lexbor/lexbor/html", "encoding.c interface.c parser.c token.c token_attr.c tokenizer.c tree.c", "dom");
-		ADD_SOURCES("ext/dom/lexbor/lexbor/encoding", "big5.c decode.c encode.c encoding.c euc_kr.c gb18030.c iso_2022_jp_katakana.c jis0208.c jis0212.c range.c res.c single.c", "dom");
+		ADD_SOURCES("ext/dom/lexbor/lexbor/encoding", "decode.c encode.c encoding.c multi.c range.c res.c single.c", "dom");
 		ADD_SOURCES("ext/dom/lexbor/lexbor/html/interfaces", "anchor_element.c area_element.c audio_element.c base_element.c body_element.c br_element.c button_element.c canvas_element.c data_element.c data_list_element.c details_element.c dialog_element.c directory_element.c div_element.c d_list_element.c document.c element.c embed_element.c field_set_element.c font_element.c form_element.c frame_element.c frame_set_element.c head_element.c heading_element.c hr_element.c html_element.c iframe_element.c image_element.c input_element.c label_element.c legend_element.c li_element.c link_element.c map_element.c marquee_element.c media_element.c menu_element.c meta_element.c meter_element.c mod_element.c object_element.c o_list_element.c opt_group_element.c option_element.c output_element.c paragraph_element.c param_element.c picture_element.c pre_element.c progress_element.c quote_element.c script_element.c select_element.c slot_element.c source_element.c span_element.c style_element.c table_caption_element.c table_cell_element.c table_col_element.c table_element.c table_row_element.c table_section_element.c template_element.c text_area_element.c time_element.c title_element.c track_element.c u_list_element.c unknown_element.c video_element.c window.c", "dom");
 		ADD_SOURCES("ext/dom/lexbor/lexbor/selectors-adapted", "selectors.c", "dom");
 		ADD_SOURCES("ext/dom/lexbor/lexbor/css", "state.c log.c parser.c css.c", "dom");

ext/dom/lexbor/lexbor/core/base.h

@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2018-2023 Alexander Borisov
+ * Copyright (C) 2018-2025 Alexander Borisov
  *
  * Author: Alexander Borisov <[email protected]>
  */
@@ -26,8 +26,8 @@ extern "C" {
 #include "lexbor/core/types.h"
 #include "lexbor/core/lexbor.h"
 
-#define LEXBOR_VERSION_MAJOR 1
-#define LEXBOR_VERSION_MINOR 7
+#define LEXBOR_VERSION_MAJOR 2
+#define LEXBOR_VERSION_MINOR 0
 #define LEXBOR_VERSION_PATCH 0
 
 #define LEXBOR_VERSION_STRING LEXBOR_STRINGIZE(LEXBOR_VERSION_MAJOR) "."       \

ext/dom/lexbor/lexbor/core/conv.c

@@ -305,13 +305,18 @@ lexbor_conv_data_to_uint(const lxb_char_t **data, size_t length)
 }
 
 size_t
-lexbor_conv_dec_to_hex(uint32_t number, lxb_char_t *out, size_t length)
+lexbor_conv_dec_to_hex(uint32_t number, lxb_char_t *out, size_t length,
+                       bool upper)
 {
     lxb_char_t c;
     size_t len;
     uint32_t tmp;
+    const lxb_char_t *map_str;
 
-    static const lxb_char_t map_str[] = "0123456789abcdef";
+    static const lxb_char_t map_str_l[] = "0123456789abcdef";
+    static const lxb_char_t map_str_u[] = "0123456789ABCDEF";
+
+    map_str = (upper) ? map_str_u : map_str_l;
 
     if(number != 0) {
         tmp = number;

ext/dom/lexbor/lexbor/core/conv.h

@@ -37,7 +37,8 @@ LXB_API unsigned
 lexbor_conv_data_to_uint(const lxb_char_t **data, size_t length);
 
 LXB_API size_t
-lexbor_conv_dec_to_hex(uint32_t number, lxb_char_t *out, size_t length);
+lexbor_conv_dec_to_hex(uint32_t number, lxb_char_t *out, size_t length,
+                       bool upper);
 
 lxb_inline long
 lexbor_conv_double_to_long(double number)

ext/dom/lexbor/lexbor/core/dobject.h

@@ -40,10 +40,6 @@ LXB_API lexbor_dobject_t *
 lexbor_dobject_destroy(lexbor_dobject_t *dobject, bool destroy_self);
 
 
-LXB_API uint8_t *
-lexbor_dobject_init_list_entries(lexbor_dobject_t *dobject, size_t pos);
-
-
 LXB_API void *
 lexbor_dobject_alloc(lexbor_dobject_t *dobject);
 

ext/dom/lexbor/lexbor/core/mraw.c

@@ -243,6 +243,8 @@ lexbor_mraw_realloc_tail(lexbor_mraw_t *mraw, void *data, void *begin,
                          size_t size, size_t begin_len, size_t new_size,
                          bool *is_valid)
 {
+    size_t length;
+    uint8_t *tmp;
     lexbor_mem_chunk_t *chunk = mraw->mem->chunk;
 
     if (chunk->size > (begin_len + new_size)) {
@@ -267,35 +269,26 @@ lexbor_mraw_realloc_tail(lexbor_mraw_t *mraw, void *data, void *begin,
      * If the tail is short then we increase the current data.
      */
     if (begin_len == lexbor_mraw_meta_size()) {
-        void *new_data;
-        lexbor_mem_chunk_t new_chunk;
-
-        *is_valid = true;
-
-        lexbor_mem_chunk_init(mraw->mem, &new_chunk,
-                              new_size + lexbor_mraw_meta_size());
-        if(new_chunk.data == NULL) {
-            return NULL;
-        }
-
-        lexbor_mraw_meta_set(new_chunk.data, &new_size);
-        new_data = lexbor_mraw_data_begin(new_chunk.data);
-
-        if (size != 0) {
-            memcpy(new_data, data, sizeof(uint8_t) * size);
-        }
-
 #if defined(LEXBOR_HAVE_ADDRESS_SANITIZER)
         ASAN_UNPOISON_MEMORY_REGION(chunk->data, chunk->size);
 #endif
+        *is_valid = true;
 
-        lexbor_mem_chunk_destroy(mraw->mem, chunk, false);
+        length = lexbor_mem_align(new_size + lexbor_mraw_meta_size()
+                                  + mraw->mem->chunk_min_size);
 
-        chunk->data = new_chunk.data;
-        chunk->size = new_chunk.size;
+        tmp = lexbor_realloc(chunk->data, length);
+        if (tmp == NULL) {
+            return NULL;
+        }
+
+        chunk->data = tmp;
+        chunk->size = length;
         chunk->length = new_size + lexbor_mraw_meta_size();
 
-        return new_data;
+        lexbor_mraw_meta_set(tmp, &new_size);
+
+        return lexbor_mraw_data_begin(tmp);
     }
 
     *is_valid = false;

ext/dom/lexbor/lexbor/core/sbst.h

@@ -25,7 +25,6 @@ extern "C" {
 # define LXB_NONSTRING
 #endif
 
-
 typedef struct {
     lxb_char_t key;
 

ext/dom/lexbor/lexbor/css/base.h

@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2019-2023 Alexander Borisov
+ * Copyright (C) 2019-2025 Alexander Borisov
  *
  * Author: Alexander Borisov <[email protected]>
  */
@@ -18,7 +18,7 @@ extern "C" {
 
 
 #define LXB_CSS_VERSION_MAJOR 1
-#define LXB_CSS_VERSION_MINOR 2
+#define LXB_CSS_VERSION_MINOR 3
 #define LXB_CSS_VERSION_PATCH 0
 
 #define LXB_CSS_VERSION_STRING                                                 \

ext/dom/lexbor/lexbor/css/parser.h

@@ -156,9 +156,6 @@ struct lxb_css_parser {
     lxb_css_syntax_token_type_t      *types_end;
     lxb_css_syntax_token_type_t      *types_pos;
 
-    lxb_css_syntax_tokenizer_chunk_f chunk_cb;
-    void                             *chunk_ctx;
-
     const lxb_char_t                 *pos;
     uintptr_t                        offset;