Sync for validator cpp engine and cpp htmlparser (#35403)

validator/cpp/htmlparser/BUILD

@@ -51,11 +51,11 @@ cc_library(
     hdrs = [
         "atomutil.h",
     ],
+    copts = ["-std=c++17"],
     deps = [
         ":atom",
         ":hash",
     ],
-    copts = ["-std=c++17"],
 )
 
 cc_test(
@@ -90,11 +90,11 @@ cc_library(
     hdrs = [
         "doctype.h",
     ],
+    copts = ["-std=c++17"],
     deps = [
         ":node",
         ":strings",
     ],
-    copts = ["-std=c++17"],
 )
 
 cc_test(
@@ -138,11 +138,11 @@ cc_library(
     hdrs = [
         "fileutil.h",
     ],
+    copts = ["-std=c++17"],
     deps = [
         ":defer",
         ":strings",
     ],
-    copts = ["-std=c++17"],
 )
 
 cc_test(
@@ -165,12 +165,12 @@ cc_library(
     hdrs = [
         "foreign.h",
     ],
+    copts = ["-std=c++17"],
     deps = [
         ":comparators",
         ":node",
         ":strings",
     ],
-    copts = ["-std=c++17"],
 )
 
 # Various hashing utility functions.
@@ -199,11 +199,11 @@ cc_library(
     hdrs = [
         "token.h",
     ],
+    copts = ["-std=c++17"],
     deps = [
         ":atom",
         ":strings",
     ],
-    copts = ["-std=c++17"],
 )
 
 # Defines node and node stack.
@@ -217,6 +217,7 @@ cc_library(
         "elements.h",
         "node.h",
     ],
+    copts = ["-std=c++17"],
     deps = [
         ":atom",
         ":atomutil",
@@ -225,7 +226,6 @@ cc_library(
         ":token",
         "@com_github_glog//:glog",
     ],
-    copts = ["-std=c++17"],
 )
 
 cc_test(
@@ -248,10 +248,10 @@ cc_library(
     hdrs = [
         "entity.h",
     ],
+    copts = ["-std=c++17"],
     deps = [
         ":comparators",
     ],
-    copts = ["-std=c++17"],
 )
 
 cc_test(
@@ -273,24 +273,24 @@ cc_library(
     hdrs = [
         "document.h",
     ],
+    copts = ["-std=c++17"],
     deps = [
         ":allocator",
         ":node",
         ":token",
         "@com_google_absl//absl/flags:flag",
     ],
-    copts = ["-std=c++17"],
 )
 
 cc_library(
     name = "casetable",
     hdrs = [
         "casetable.h",
     ],
+    copts = ["-std=c++17"],
     deps = [
         ":comparators",
     ],
-    copts = ["-std=c++17"],
 )
 
 cc_test(
@@ -314,6 +314,7 @@ cc_library(
     hdrs = [
         "parser.h",
     ],
+    copts = ["-std=c++17"],
     deps = [
         ":atom",
         ":atomutil",
@@ -326,11 +327,10 @@ cc_library(
         ":node",
         ":strings",
         ":tokenizer",
+        "@com_github_glog//:glog",
         "@com_google_absl//absl/base",
         "@com_google_absl//absl/flags:flag",
-        "@com_github_glog//:glog",
     ],
-    copts = ["-std=c++17"],
 )
 
 cc_test(
@@ -359,12 +359,12 @@ cc_library(
     hdrs = [
         "renderer.h",
     ],
+    copts = ["-std=c++17"],
     deps = [
         ":atomutil",
         ":node",
         ":strings",
     ],
-    copts = ["-std=c++17"],
 )
 
 cc_test(
@@ -396,15 +396,15 @@ cc_library(
     hdrs = [
         "strings.h",
     ],
+    copts = ["-std=c++17"],
     deps = [
         ":casetable",
         ":htmlentities",
         ":logging",
         ":whitespacetable",
-        "@com_google_absl//absl/base",
         "@com_github_glog//:glog",
+        "@com_google_absl//absl/base",
     ],
-    copts = ["-std=c++17"],
 )
 
 cc_test(
@@ -427,6 +427,7 @@ cc_library(
     hdrs = [
         "tokenizer.h",
     ],
+    copts = ["-std=c++17"],
     deps = [
         ":atom",
         ":atomutil",
@@ -435,7 +436,6 @@ cc_library(
         ":token",
         "@com_google_absl//absl/flags:flag",
     ],
-    copts = ["-std=c++17"],
 )
 
 cc_test(
@@ -459,10 +459,10 @@ cc_library(
     hdrs = [
         "url.h",
     ],
+    copts = ["-std=c++17"],
     deps = [
         ":strings",
     ],
-    copts = ["-std=c++17"],
 )
 
 cc_test(
@@ -491,8 +491,10 @@ filegroup(
 
 filegroup(
     name = "html5lib_test_files",
-    srcs = glob(["testdata/tree-construction/*.dat",
-                 "testdata/tree-construction/scripted/*.dat"]),
+    srcs = glob([
+        "testdata/tree-construction/*.dat",
+        "testdata/tree-construction/scripted/*.dat",
+    ]),
 )
 
 cc_test(

validator/cpp/htmlparser/bin/statetablegen.cc

@@ -24,7 +24,6 @@
 
 #include <iostream>
 
-#include "glog/logging.h"
 #include "absl/flags/flag.h"
 #include "absl/flags/parse.h"
 #include "grammar/tablebuilder.h"

validator/cpp/htmlparser/css/BUILD

@@ -6,7 +6,7 @@
 #
 # bazel build --repo_env=CC=clang --cxxopt='-std=c++17' <build_target>
 
-load("@rules_cc//cc:defs.bzl", "cc_library", "cc_test", "cc_proto_library")
+load("@rules_cc//cc:defs.bzl", "cc_library", "cc_proto_library", "cc_test")
 load("@rules_proto//proto:defs.bzl", "proto_library")
 
 package(default_visibility = ["//visibility:public"])
@@ -96,9 +96,9 @@ cc_library(
     hdrs = ["amp4ads-parse-css.h"],
     deps = [
         ":parse-css",
+        "@com_github_re2//:re2",
         "@com_google_absl//absl/memory",
         "@com_google_absl//absl/strings",
-        "@com_github_re2//:re2",
     ],
 )
 

validator/cpp/htmlparser/css/amp4ads-parse-css_test.cc

@@ -16,8 +16,7 @@
 
 #include "css/amp4ads-parse-css.h"
 
-#include "glog/logging.h"
-#include "gmock/gmock.h"
+#include <gmock/gmock.h>
 #include "gtest/gtest.h"
 #include "absl/strings/str_cat.h"
 #include "absl/strings/str_join.h"

validator/cpp/htmlparser/css/parse-css-urls.cc

@@ -18,13 +18,13 @@
 
 #include <memory>
 
-#include "glog/logging.h"
 #include "absl/algorithm/container.h"
 #include "absl/memory/memory.h"
 #include "absl/strings/ascii.h"
 #include "absl/strings/numbers.h"
 #include "absl/strings/str_join.h"
 #include "absl/types/variant.h"
+#include "logging.h"
 #include "strings.h"
 
 using absl::AsciiStrToLower;
@@ -157,9 +157,8 @@ class Tokenizer {
   }
 
   char32_t Next(int num = 1) {
-    CHECK_GE(num, 0);
-    CHECK_LE(num, 3)
-        << "Spec Error; no more than three codepoints of lookahead.";
+    CHECK(num >= 0, "Spec Error; negative lookahead.");
+    CHECK(num <= 3, "Spec Error; no more than three codepoints of lookahead.");
     return Codepoint(pos_ + num);
   }
 
@@ -181,9 +180,7 @@ class Tokenizer {
     return true;
   }
 
-  bool EofNext(int num = 1) {
-    return pos_ + num >= str_.size();
-  }
+  bool EofNext(int num = 1) { return pos_ + num >= str_.size(); }
 
   bool Eof() { return eof_; }
 
@@ -453,8 +450,8 @@ class Tokenizer {
       }
       if (Whitespace(Next())) Consume();
       uint32_t value;
-      if (!absl::numbers_internal::safe_strtou32_base(
-          digits, &value, /*base=*/16)) {
+      if (!absl::numbers_internal::safe_strtou32_base(digits, &value,
+                                                      /*base=*/16)) {
         value = 0xfffd;
       }
       if (value > kMaximumallowedcodepoint) value = 0xfffd;
@@ -597,8 +594,7 @@ int ConsumeAComponentValue(const vector<unique_ptr<Token>>& tokens,
 
 TokenType::Code TypeOrEof(const vector<unique_ptr<Token>>& tokens,
                           const int pos) {
-  if (pos < tokens.size())
-    return tokens[pos]->Type();
+  if (pos < tokens.size()) return tokens[pos]->Type();
   return tokens[tokens.size() - 1]->Type();
 }
 
@@ -634,7 +630,7 @@ int ConsumeABlock(const vector<unique_ptr<Token>>& tokens,
 int ConsumeAComponentValue(const vector<unique_ptr<Token>>& tokens,
                            const int start_pos) {
   TokenType::Code type = TypeOrEof(tokens, start_pos);
-  CHECK_NE(type, TokenType::EOF_TOKEN);
+  CHECK(type != TokenType::EOF_TOKEN, "");
   if (type == TokenType::OPEN_CURLY || type == TokenType::OPEN_SQUARE ||
       type == TokenType::OPEN_PAREN || type == TokenType::FUNCTION_TOKEN) {
     return ConsumeABlock(tokens, start_pos);
@@ -647,11 +643,11 @@ int ConsumeAComponentValue(const vector<unique_ptr<Token>>& tokens,
 // starts at position |start_pos|.
 int ConsumeAFontFace(const vector<unique_ptr<Token>>& tokens,
                      const int start_pos) {
-  CHECK_EQ(TypeOrEof(tokens, start_pos), TokenType::AT_KEYWORD)
-      << TokenType::Code_Name(TypeOrEof(tokens, start_pos));
-  CHECK_EQ(static_cast<const AtKeywordToken&>(*tokens[start_pos]).StringValue(),
-           "font-face")
-      << static_cast<const AtKeywordToken&>(*tokens[start_pos]).StringValue();
+  CHECK(TypeOrEof(tokens, start_pos) == TokenType::AT_KEYWORD,
+        TokenType::Code_Name(TypeOrEof(tokens, start_pos)));
+  CHECK(static_cast<const AtKeywordToken&>(*tokens[start_pos]).StringValue() ==
+            "font-face",
+        static_cast<const AtKeywordToken&>(*tokens[start_pos]).StringValue());
   int cur_pos = start_pos;
   while (true) {
     cur_pos++;
@@ -669,7 +665,7 @@ int ConsumeAFontFace(const vector<unique_ptr<Token>>& tokens,
 int ConsumeAUrlFunction(const vector<unique_ptr<Token>>& tokens,
                         const int start_pos, std::string* url) {
   TokenType::Code type = TypeOrEof(tokens, start_pos);
-  CHECK_EQ(type, TokenType::FUNCTION_TOKEN) << TokenType::Code_Name(type);
+  CHECK(type == TokenType::FUNCTION_TOKEN, TokenType::Code_Name(type));
   int cur_pos = start_pos;
   *url = "";
   while (true) {
@@ -694,8 +690,7 @@ int ConsumeAUrlFunction(const vector<unique_ptr<Token>>& tokens,
   return ConsumeABlock(tokens, start_pos);
 }
 
-bool SegmentCss(const std::string& utf8_css,
-                vector<CssSegment>* segments) {
+bool SegmentCss(const std::string& utf8_css, vector<CssSegment>* segments) {
   // This changes the input string into an array of UTF8 Codepoints. Each
   // codepoint can match one or more bytes in the input string.
   vector<char32_t> css = htmlparser::Strings::Utf8ToCodepoints(utf8_css);
@@ -706,8 +701,7 @@ bool SegmentCss(const std::string& utf8_css,
   const vector<unique_ptr<Token>> tokens = url::Tokenize(css, &errors);
 
   // Documents with CSS errors are invalid AMP, so we can just exit early.
-  if (!errors.empty())
-    return false;
+  if (!errors.empty()) return false;
 
   // This code includes limited CSS parsing. The reason it works is that we
   // can assume that the input is valid CSS. It might not be, but if it isn't
@@ -757,8 +751,7 @@ bool SegmentCss(const std::string& utf8_css,
         segments->emplace_back(segment);
       }
 
-      // Safe: |tokens| ends w/ EOF_TOKEN.
-      CHECK_LT(cur_pos + 1, tokens.size());
+      CHECK(cur_pos + 1 < tokens.size(), "tokens missing EOF_TOKEN");
       // Set our next range start to the start of the next token.
       css_chars_emitted_until = tokens[cur_pos + 1]->pos();
     }

validator/cpp/htmlparser/css/parse-css-urls.h

@@ -34,8 +34,6 @@
 #include "absl/memory/memory.h"
 #include "absl/types/variant.h"
 #include "css/parse-css-urls.pb.h"
-#include "validator.pb.h"
-
 
 namespace htmlparser::css::url {
 // Implements 3.3. Preprocessing the input stream.

validator/cpp/htmlparser/css/parse-css-urls_test.cc

@@ -17,8 +17,8 @@
 #include "css/parse-css-urls.h"
 
 #include <ostream>
-#include "glog/logging.h"
-#include "gmock/gmock.h"
+
+#include <gmock/gmock.h>
 #include "gtest/gtest.h"
 #include "absl/strings/str_cat.h"
 #include "strings.h"