LibWeb: Implement more CSS serializers and make them more ergonomic

This implements these algorithms from the CSSOM-1 spec:
- serialize a string
- serialize a URL

Also, we now have two versions of each of the serialization functions:
One that returns a String as before, and the other that takes a
StringBuilder to write into. This saves creating extra StringBuilders
when they are not needed. :^)
This commit is contained in:
Sam Atkins 2021-10-14 16:50:43 +01:00 committed by Linus Groh
parent 5c1427f3e0
commit 75c9313d7d
Notes: sideshowbarker 2024-07-18 02:18:27 +09:00
2 changed files with 94 additions and 13 deletions

View File

@ -11,24 +11,21 @@
namespace Web::CSS {
// https://www.w3.org/TR/cssom-1/#escape-a-character
String escape_a_character(u32 character)
void escape_a_character(StringBuilder builder, u32 character)
{
StringBuilder builder;
builder.append('\\');
builder.append_code_point(character);
return builder.to_string();
}
// https://www.w3.org/TR/cssom-1/#escape-a-character-as-code-point
String escape_a_character_as_code_point(u32 character)
void escape_a_character_as_code_point(StringBuilder builder, u32 character)
{
return String::formatted("\\{:x} ", character);
builder.appendff("\\{:x} ", character);
}
// https://www.w3.org/TR/cssom-1/#serialize-an-identifier
String serialize_an_identifier(StringView const& ident)
void serialize_an_identifier(StringBuilder builder, StringView const& ident)
{
StringBuilder builder;
Utf8View characters { ident };
auto first_character = characters.is_empty() ? 0 : *characters.begin();
@ -43,25 +40,25 @@ String serialize_an_identifier(StringView const& ident)
// If the character is in the range [\1-\1f] (U+0001 to U+001F) or is U+007F,
// then the character escaped as code point.
if ((character >= 0x0001 && character <= 0x001F) || (character == 0x007F)) {
builder.append(escape_a_character_as_code_point(character));
escape_a_character_as_code_point(builder, character);
continue;
}
// If the character is the first character and is in the range [0-9] (U+0030 to U+0039),
// then the character escaped as code point.
if (builder.is_empty() && character >= '0' && character <= '9') {
builder.append(escape_a_character_as_code_point(character));
escape_a_character_as_code_point(builder, character);
continue;
}
// If the character is the second character and is in the range [0-9] (U+0030 to U+0039)
// and the first character is a "-" (U+002D), then the character escaped as code point.
if (builder.length() == 1 && first_character == '-' && character >= '0' && character <= '9') {
builder.append(escape_a_character_as_code_point(character));
escape_a_character_as_code_point(builder, character);
continue;
}
// If the character is the first character and is a "-" (U+002D), and there is no second
// character, then the escaped character.
if (builder.is_empty() && character == '-' && characters.length() == 1) {
builder.append(escape_a_character(character));
escape_a_character(builder, character);
continue;
}
// If the character is not handled by one of the above rules and is greater than or equal to U+0080, is "-" (U+002D) or "_" (U+005F), or is in one of the ranges [0-9] (U+0030 to U+0039), [A-Z] (U+0041 to U+005A), or \[a-z] (U+0061 to U+007A), then the character itself.
@ -74,8 +71,84 @@ String serialize_an_identifier(StringView const& ident)
continue;
}
// Otherwise, the escaped character.
builder.append(escape_a_character(character));
escape_a_character(builder, character);
}
}
// https://www.w3.org/TR/cssom-1/#serialize-a-string
void serialize_a_string(StringBuilder builder, StringView const& string)
{
Utf8View characters { string };
// To serialize a string means to create a string represented by '"' (U+0022), followed by the result
// of applying the rules below to each character of the given string, followed by '"' (U+0022):
builder.append('"');
for (auto character : characters) {
// If the character is NULL (U+0000), then the REPLACEMENT CHARACTER (U+FFFD).
if (character == 0) {
builder.append_code_point(0xFFFD);
continue;
}
// If the character is in the range [\1-\1f] (U+0001 to U+001F) or is U+007F, the character escaped as code point.
if ((character >= 0x0001 && character <= 0x001F) || (character == 0x007F)) {
escape_a_character_as_code_point(builder, character);
continue;
}
// If the character is '"' (U+0022) or "\" (U+005C), the escaped character.
if (character == 0x0022 || character == 0x005C) {
escape_a_character(builder, character);
continue;
}
// Otherwise, the character itself.
builder.append_code_point(character);
}
builder.append('"');
}
// https://www.w3.org/TR/cssom-1/#serialize-a-url
void serialize_a_url(StringBuilder builder, StringView const& url)
{
// To serialize a URL means to create a string represented by "url(",
// followed by the serialization of the URL as a string, followed by ")".
builder.append("url(");
serialize_a_string(builder, url.to_string());
builder.append(')');
}
String escape_a_character(u32 character)
{
StringBuilder builder;
escape_a_character(builder, character);
return builder.to_string();
}
String escape_a_character_as_code_point(u32 character)
{
StringBuilder builder;
escape_a_character_as_code_point(builder, character);
return builder.to_string();
}
String serialize_an_identifier(StringView const& ident)
{
StringBuilder builder;
serialize_an_identifier(builder, ident);
return builder.to_string();
}
String serialize_a_string(StringView const& string)
{
StringBuilder builder;
serialize_a_string(builder, string);
return builder.to_string();
}
String serialize_a_url(StringView const& url)
{
StringBuilder builder;
serialize_a_url(builder, url);
return builder.to_string();
}

View File

@ -7,13 +7,21 @@
#pragma once
#include <AK/String.h>
#include <AK/StringBuilder.h>
#include <AK/StringView.h>
namespace Web::CSS {
void escape_a_character(StringBuilder, u32 character);
void escape_a_character_as_code_point(StringBuilder, u32 character);
void serialize_an_identifier(StringBuilder, StringView const& ident);
void serialize_a_string(StringBuilder, StringView const& string);
void serialize_a_url(StringBuilder, StringView const& url);
String escape_a_character(u32 character);
String escape_a_character_as_code_point(u32 character);
String serialize_an_identifier(StringView const& ident);
String serialize_a_string(StringView const& string);
String serialize_a_url(StringView const& url);
}