for maximal portability, use only ASCII (#905)

Author: lemire

benchmarks/percent_encode.cpp

@@ -9,7 +9,7 @@ size_t N = 1000;
 
 #include <benchmark/benchmark.h>
 
-std::string examples[] = {"á|", "other:9818274x1!!",
+std::string examples[] = {"\xE1|", "other:9818274x1!!",
                           "ref=web-twc-ao-gbl-adsinfo&utm_source=twc&utm_",
                           "connect_timeout=10&application_name=myapp"};
 

include/ada/parser-inl.h

@@ -65,7 +65,7 @@ tl::expected<url_pattern<regex_provider>, errors> parse_url_pattern_impl(
     return tl::unexpected(processed_init.error());
   }
 
-  // For each componentName of « "protocol", "username", "password", "hostname",
+  // For each componentName of  "protocol", "username", "password", "hostname",
   // "port", "pathname", "search", "hash" If processedInit[componentName] does
   // not exist, then set processedInit[componentName] to "*".
   ADA_ASSERT_TRUE(processed_init.has_value());
@@ -103,7 +103,7 @@ tl::expected<url_pattern<regex_provider>, errors> parse_url_pattern_impl(
   // Let urlPattern be a new URL pattern.
   url_pattern<regex_provider> url_pattern_{};
 
-  // Set urlPattern’s protocol component to the result of compiling a component
+  // Set urlPattern's protocol component to the result of compiling a component
   // given processedInit["protocol"], canonicalize a protocol, and default
   // options.
   auto protocol_component = url_pattern_component<regex_provider>::compile(
@@ -117,7 +117,7 @@ tl::expected<url_pattern<regex_provider>, errors> parse_url_pattern_impl(
   }
   url_pattern_.protocol_component = std::move(*protocol_component);
 
-  // Set urlPattern’s username component to the result of compiling a component
+  // Set urlPattern's username component to the result of compiling a component
   // given processedInit["username"], canonicalize a username, and default
   // options.
   auto username_component = url_pattern_component<regex_provider>::compile(
@@ -131,7 +131,7 @@ tl::expected<url_pattern<regex_provider>, errors> parse_url_pattern_impl(
   }
   url_pattern_.username_component = std::move(*username_component);
 
-  // Set urlPattern’s password component to the result of compiling a component
+  // Set urlPattern's password component to the result of compiling a component
   // given processedInit["password"], canonicalize a password, and default
   // options.
   auto password_component = url_pattern_component<regex_provider>::compile(
@@ -148,12 +148,12 @@ tl::expected<url_pattern<regex_provider>, errors> parse_url_pattern_impl(
   // TODO: Optimization opportunity. The following if statement can be
   // simplified.
   // If the result running hostname pattern is an IPv6 address given
-  // processedInit["hostname"] is true, then set urlPattern’s hostname component
+  // processedInit["hostname"] is true, then set urlPattern's hostname component
   // to the result of compiling a component given processedInit["hostname"],
   // canonicalize an IPv6 hostname, and hostname options.
   if (url_pattern_helpers::is_ipv6_address(processed_init->hostname.value())) {
     ada_log("processed_init->hostname is ipv6 address");
-    // then set urlPattern’s hostname component to the result of compiling a
+    // then set urlPattern's hostname component to the result of compiling a
     // component given processedInit["hostname"], canonicalize an IPv6 hostname,
     // and hostname options.
     auto hostname_component = url_pattern_component<regex_provider>::compile(
@@ -167,7 +167,7 @@ tl::expected<url_pattern<regex_provider>, errors> parse_url_pattern_impl(
     }
     url_pattern_.hostname_component = std::move(*hostname_component);
   } else {
-    // Otherwise, set urlPattern’s hostname component to the result of compiling
+    // Otherwise, set urlPattern's hostname component to the result of compiling
     // a component given processedInit["hostname"], canonicalize a hostname, and
     // hostname options.
     auto hostname_component = url_pattern_component<regex_provider>::compile(
@@ -182,7 +182,7 @@ tl::expected<url_pattern<regex_provider>, errors> parse_url_pattern_impl(
     url_pattern_.hostname_component = std::move(*hostname_component);
   }
 
-  // Set urlPattern’s port component to the result of compiling a component
+  // Set urlPattern's port component to the result of compiling a component
   // given processedInit["port"], canonicalize a port, and default options.
   auto port_component = url_pattern_component<regex_provider>::compile(
       processed_init->port.value(), url_pattern_helpers::canonicalize_port,
@@ -203,7 +203,7 @@ tl::expected<url_pattern<regex_provider>, errors> parse_url_pattern_impl(
 
   // TODO: Optimization opportunity: Simplify this if statement.
   // If the result of running protocol component matches a special scheme given
-  // urlPattern’s protocol component is true, then:
+  // urlPattern's protocol component is true, then:
   if (url_pattern_helpers::protocol_component_matches_special_scheme<
           regex_provider>(url_pattern_.protocol_component)) {
     // Let pathCompileOptions be copy of the pathname options with the ignore
@@ -213,7 +213,7 @@ tl::expected<url_pattern<regex_provider>, errors> parse_url_pattern_impl(
       path_compile_options.ignore_case = options->ignore_case;
     }
 
-    // Set urlPattern’s pathname component to the result of compiling a
+    // Set urlPattern's pathname component to the result of compiling a
     // component given processedInit["pathname"], canonicalize a pathname, and
     // pathCompileOptions.
     auto pathname_component = url_pattern_component<regex_provider>::compile(
@@ -226,7 +226,7 @@ tl::expected<url_pattern<regex_provider>, errors> parse_url_pattern_impl(
     }
     url_pattern_.pathname_component = std::move(*pathname_component);
   } else {
-    // Otherwise set urlPattern’s pathname component to the result of compiling
+    // Otherwise set urlPattern's pathname component to the result of compiling
     // a component given processedInit["pathname"], canonicalize an opaque
     // pathname, and compileOptions.
     auto pathname_component = url_pattern_component<regex_provider>::compile(
@@ -240,7 +240,7 @@ tl::expected<url_pattern<regex_provider>, errors> parse_url_pattern_impl(
     url_pattern_.pathname_component = std::move(*pathname_component);
   }
 
-  // Set urlPattern’s search component to the result of compiling a component
+  // Set urlPattern's search component to the result of compiling a component
   // given processedInit["search"], canonicalize a search, and compileOptions.
   auto search_component = url_pattern_component<regex_provider>::compile(
       processed_init->search.value(), url_pattern_helpers::canonicalize_search,
@@ -252,7 +252,7 @@ tl::expected<url_pattern<regex_provider>, errors> parse_url_pattern_impl(
   }
   url_pattern_.search_component = std::move(*search_component);
 
-  // Set urlPattern’s hash component to the result of compiling a component
+  // Set urlPattern's hash component to the result of compiling a component
   // given processedInit["hash"], canonicalize a hash, and compileOptions.
   auto hash_component = url_pattern_component<regex_provider>::compile(
       processed_init->hash.value(), url_pattern_helpers::canonicalize_hash,

include/ada/url_pattern-inl.h

@@ -179,7 +179,7 @@ url_pattern_component<regex_provider>::compile(
   }
 
   // For each part of part list:
-  // - If part’s type is "regexp", then set has regexp groups to true.
+  // - If part's type is "regexp", then set has regexp groups to true.
   const auto has_regexp = [](const auto& part) { return part.is_regexp(); };
   const bool has_regexp_groups = std::ranges::any_of(*part_list, has_regexp);
 
@@ -326,32 +326,32 @@ result<std::optional<url_pattern_result>> url_pattern<regex_provider>::match(
       return std::nullopt;
     }
 
-    // Set protocol to url’s scheme.
+    // Set protocol to url's scheme.
     // IMPORTANT: Not documented on the URLPattern spec, but protocol suffix ':'
     // is removed. Similar work was done on workerd:
     // https://github.com/cloudflare/workerd/blob/8620d14012513a6ce04d079e401d3becac3c67bd/src/workerd/jsg/url.c%2B%2B#L2038
     protocol = url->get_protocol().substr(0, url->get_protocol().size() - 1);
-    // Set username to url’s username.
+    // Set username to url's username.
     username = url->get_username();
-    // Set password to url’s password.
+    // Set password to url's password.
     password = url->get_password();
-    // Set hostname to url’s host, serialized, or the empty string if the value
+    // Set hostname to url's host, serialized, or the empty string if the value
     // is null.
     hostname = url->get_hostname();
-    // Set port to url’s port, serialized, or the empty string if the value is
+    // Set port to url's port, serialized, or the empty string if the value is
     // null.
     port = url->get_port();
     // Set pathname to the result of URL path serializing url.
     pathname = url->get_pathname();
-    // Set search to url’s query or the empty string if the value is null.
+    // Set search to url's query or the empty string if the value is null.
     // IMPORTANT: Not documented on the URLPattern spec, but search prefix '?'
     // is removed. Similar work was done on workerd:
     // https://github.com/cloudflare/workerd/blob/8620d14012513a6ce04d079e401d3becac3c67bd/src/workerd/jsg/url.c%2B%2B#L2232
     if (url->has_search()) {
       auto view = url->get_search();
       search = view.starts_with("?") ? url->get_search().substr(1) : view;
     }
-    // Set hash to url’s fragment or the empty string if the value is null.
+    // Set hash to url's fragment or the empty string if the value is null.
     // IMPORTANT: Not documented on the URLPattern spec, but hash prefix '#' is
     // removed. Similar work was done on workerd:
     // https://github.com/cloudflare/workerd/blob/8620d14012513a6ce04d079e401d3becac3c67bd/src/workerd/jsg/url.c%2B%2B#L2242
@@ -361,7 +361,7 @@ result<std::optional<url_pattern_result>> url_pattern<regex_provider>::match(
     }
   }
 
-  // Let protocolExecResult be RegExpBuiltinExec(urlPattern’s protocol
+  // Let protocolExecResult be RegExpBuiltinExec(urlPattern's protocol
   // component's regular expression, protocol).
   auto protocol_exec_result =
       regex_provider::regex_search(protocol, protocol_component.regexp);
@@ -370,7 +370,7 @@ result<std::optional<url_pattern_result>> url_pattern<regex_provider>::match(
     return std::nullopt;
   }
 
-  // Let usernameExecResult be RegExpBuiltinExec(urlPattern’s username
+  // Let usernameExecResult be RegExpBuiltinExec(urlPattern's username
   // component's regular expression, username).
   auto username_exec_result =
       regex_provider::regex_search(username, username_component.regexp);
@@ -379,7 +379,7 @@ result<std::optional<url_pattern_result>> url_pattern<regex_provider>::match(
     return std::nullopt;
   }
 
-  // Let passwordExecResult be RegExpBuiltinExec(urlPattern’s password
+  // Let passwordExecResult be RegExpBuiltinExec(urlPattern's password
   // component's regular expression, password).
   auto password_exec_result =
       regex_provider::regex_search(password, password_component.regexp);
@@ -388,7 +388,7 @@ result<std::optional<url_pattern_result>> url_pattern<regex_provider>::match(
     return std::nullopt;
   }
 
-  // Let hostnameExecResult be RegExpBuiltinExec(urlPattern’s hostname
+  // Let hostnameExecResult be RegExpBuiltinExec(urlPattern's hostname
   // component's regular expression, hostname).
   auto hostname_exec_result =
       regex_provider::regex_search(hostname, hostname_component.regexp);
@@ -397,7 +397,7 @@ result<std::optional<url_pattern_result>> url_pattern<regex_provider>::match(
     return std::nullopt;
   }
 
-  // Let portExecResult be RegExpBuiltinExec(urlPattern’s port component's
+  // Let portExecResult be RegExpBuiltinExec(urlPattern's port component's
   // regular expression, port).
   auto port_exec_result =
       regex_provider::regex_search(port, port_component.regexp);
@@ -406,7 +406,7 @@ result<std::optional<url_pattern_result>> url_pattern<regex_provider>::match(
     return std::nullopt;
   }
 
-  // Let pathnameExecResult be RegExpBuiltinExec(urlPattern’s pathname
+  // Let pathnameExecResult be RegExpBuiltinExec(urlPattern's pathname
   // component's regular expression, pathname).
   auto pathname_exec_result =
       regex_provider::regex_search(pathname, pathname_component.regexp);
@@ -415,7 +415,7 @@ result<std::optional<url_pattern_result>> url_pattern<regex_provider>::match(
     return std::nullopt;
   }
 
-  // Let searchExecResult be RegExpBuiltinExec(urlPattern’s search component's
+  // Let searchExecResult be RegExpBuiltinExec(urlPattern's search component's
   // regular expression, search).
   auto search_exec_result =
       regex_provider::regex_search(search, search_component.regexp);
@@ -424,7 +424,7 @@ result<std::optional<url_pattern_result>> url_pattern<regex_provider>::match(
     return std::nullopt;
   }
 
-  // Let hashExecResult be RegExpBuiltinExec(urlPattern’s hash component's
+  // Let hashExecResult be RegExpBuiltinExec(urlPattern's hash component's
   // regular expression, hash).
   auto hash_exec_result =
       regex_provider::regex_search(hash, hash_component.regexp);
@@ -438,42 +438,42 @@ result<std::optional<url_pattern_result>> url_pattern<regex_provider>::match(
   // Set result["inputs"] to inputs.
   result.inputs = std::move(inputs);
   // Set result["protocol"] to the result of creating a component match result
-  // given urlPattern’s protocol component, protocol, and protocolExecResult.
+  // given urlPattern's protocol component, protocol, and protocolExecResult.
   result.protocol = protocol_component.create_component_match_result(
       std::move(protocol), std::move(*protocol_exec_result));
 
   // Set result["username"] to the result of creating a component match result
-  // given urlPattern’s username component, username, and usernameExecResult.
+  // given urlPattern's username component, username, and usernameExecResult.
   result.username = username_component.create_component_match_result(
       std::move(username), std::move(*username_exec_result));
 
   // Set result["password"] to the result of creating a component match result
-  // given urlPattern’s password component, password, and passwordExecResult.
+  // given urlPattern's password component, password, and passwordExecResult.
   result.password = password_component.create_component_match_result(
       std::move(password), std::move(*password_exec_result));
 
   // Set result["hostname"] to the result of creating a component match result
-  // given urlPattern’s hostname component, hostname, and hostnameExecResult.
+  // given urlPattern's hostname component, hostname, and hostnameExecResult.
   result.hostname = hostname_component.create_component_match_result(
       std::move(hostname), std::move(*hostname_exec_result));
 
   // Set result["port"] to the result of creating a component match result given
-  // urlPattern’s port component, port, and portExecResult.
+  // urlPattern's port component, port, and portExecResult.
   result.port = port_component.create_component_match_result(
       std::move(port), std::move(*port_exec_result));
 
   // Set result["pathname"] to the result of creating a component match result
-  // given urlPattern’s pathname component, pathname, and pathnameExecResult.
+  // given urlPattern's pathname component, pathname, and pathnameExecResult.
   result.pathname = pathname_component.create_component_match_result(
       std::move(pathname), std::move(*pathname_exec_result));
 
   // Set result["search"] to the result of creating a component match result
-  // given urlPattern’s search component, search, and searchExecResult.
+  // given urlPattern's search component, search, and searchExecResult.
   result.search = search_component.create_component_match_result(
       std::move(search), std::move(*search_exec_result));
 
   // Set result["hash"] to the result of creating a component match result given
-  // urlPattern’s hash component, hash, and hashExecResult.
+  // urlPattern's hash component, hash, and hashExecResult.
   result.hash = hash_component.create_component_match_result(
       std::move(hash), std::move(*hash_exec_result));