rbs 3.9.5 → 3.10.0.pre.1

data/src/util/rbs_unescape.c

@@ -0,0 +1,131 @@
+#include "rbs/util/rbs_unescape.h"
+#include <string.h>
+#include <stdlib.h>
+#include <ctype.h>
+
+// Define the escape character mappings
+// TODO: use a switch instead
+static const struct {
+    const char *from;
+    const char *to;
+} TABLE[] = {
+    { "\\a", "\a" },
+    { "\\b", "\b" },
+    { "\\e", "\033" },
+    { "\\f", "\f" },
+    { "\\n", "\n" },
+    { "\\r", "\r" },
+    { "\\s", " " },
+    { "\\t", "\t" },
+    { "\\v", "\v" },
+    { "\\\"", "\"" },
+    { "\\'", "'" },
+    { "\\\\", "\\" },
+    { "\\", "" }
+};
+
+// Helper function to convert hex string to integer
+static int hex_to_int(const char *hex, int length) {
+    int result = 0;
+    for (int i = 0; i < length; i++) {
+        result = result * 16 + (isdigit(hex[i]) ? hex[i] - '0' : tolower(hex[i]) - 'a' + 10);
+    }
+    return result;
+}
+
+// Helper function to convert octal string to integer
+static int octal_to_int(const char *octal, int length) {
+    int result = 0;
+    for (int i = 0; i < length; i++) {
+        result = result * 8 + (octal[i] - '0');
+    }
+    return result;
+}
+
+int rbs_utf8_codelen(unsigned int c) {
+    if (c <= 0x7F) return 1;
+    if (c <= 0x7FF) return 2;
+    if (c <= 0xFFFF) return 3;
+    if (c <= 0x10FFFF) return 4;
+    return 1; // Invalid Unicode codepoint, treat as 1 byte
+}
+
+rbs_string_t unescape_string(rbs_allocator_t *allocator, const rbs_string_t string, bool is_double_quote) {
+    if (!string.start) return RBS_STRING_NULL;
+
+    size_t len = string.end - string.start;
+    const char *input = string.start;
+
+    char *output = rbs_allocator_alloc_many(allocator, len + 1, char);
+    if (!output) return RBS_STRING_NULL;
+
+    size_t i = 0, j = 0;
+    while (i < len) {
+        if (input[i] == '\\' && i + 1 < len) {
+            if (is_double_quote) {
+                if (isdigit(input[i + 1])) {
+                    // Octal escape
+                    int octal_len = 1;
+                    while (octal_len < 3 && i + 1 + octal_len < len && isdigit(input[i + 1 + octal_len]))
+                        octal_len++;
+                    int value = octal_to_int(input + i + 1, octal_len);
+                    output[j++] = (char) value;
+                    i += octal_len + 1;
+                } else if (input[i + 1] == 'x' && i + 3 < len) {
+                    // Hex escape
+                    int hex_len = isxdigit(input[i + 3]) ? 2 : 1;
+                    int value = hex_to_int(input + i + 2, hex_len);
+                    output[j++] = (char) value;
+                    i += hex_len + 2;
+                } else if (input[i + 1] == 'u' && i + 5 < len) {
+                    // Unicode escape
+                    int value = hex_to_int(input + i + 2, 4);
+                    output[j++] = (char) value;
+                    i += 6;
+                } else {
+                    // Other escapes
+                    int found = 0;
+                    for (size_t k = 0; k < sizeof(TABLE) / sizeof(TABLE[0]); k++) {
+                        if (strncmp(input + i, TABLE[k].from, strlen(TABLE[k].from)) == 0) {
+                            output[j++] = TABLE[k].to[0];
+                            i += strlen(TABLE[k].from);
+                            found = 1;
+                            break;
+                        }
+                    }
+                    if (!found) {
+                        output[j++] = input[i++];
+                    }
+                }
+            } else {
+                /* Single quote: only escape ' and \ */
+                if (input[i + 1] == '\'' || input[i + 1] == '\\') {
+                    output[j++] = input[i + 1];
+                    i += 2;
+                } else {
+                    output[j++] = input[i++];
+                }
+            }
+        } else {
+            output[j++] = input[i++];
+        }
+    }
+    output[j] = '\0';
+    return rbs_string_new(output, output + j);
+}
+
+rbs_string_t rbs_unquote_string(rbs_allocator_t *allocator, rbs_string_t input) {
+    unsigned int first_char = rbs_utf8_string_to_codepoint(input);
+    size_t byte_length = rbs_string_len(input);
+
+    ptrdiff_t start_offset = 0;
+    if (first_char == '"' || first_char == '\'' || first_char == '`') {
+        int bs = rbs_utf8_codelen(first_char);
+        start_offset += bs;
+        byte_length -= 2 * bs;
+    }
+
+    const char *new_start = input.start + start_offset;
+    rbs_string_t string = rbs_string_new(new_start, new_start + byte_length);
+    return unescape_string(allocator, string, first_char == '"');
+}

data/stdlib/cgi/0/core.rbs

@@ -1,274 +1,5 @@
-# <!-- rdoc-file=lib/cgi.rb -->
-# ## Overview
-#
-# The Common Gateway Interface (CGI) is a simple protocol for passing an HTTP
-# request from a web server to a standalone program, and returning the output to
-# the web browser.  Basically, a CGI program is called with the parameters of
-# the request passed in either in the environment (GET) or via $stdin (POST),
-# and everything it prints to $stdout is returned to the client.
-#
-# This file holds the CGI class.  This class provides functionality for
-# retrieving HTTP request parameters, managing cookies, and generating HTML
-# output.
-#
-# The file CGI::Session provides session management functionality; see that
-# class for more details.
-#
-# See http://www.w3.org/CGI/ for more information on the CGI protocol.
-#
-# ## Introduction
-#
-# CGI is a large class, providing several categories of methods, many of which
-# are mixed in from other modules.  Some of the documentation is in this class,
-# some in the modules CGI::QueryExtension and CGI::HtmlExtension.  See
-# CGI::Cookie for specific information on handling cookies, and cgi/session.rb
-# (CGI::Session) for information on sessions.
-#
-# For queries, CGI provides methods to get at environmental variables,
-# parameters, cookies, and multipart request data.  For responses, CGI provides
-# methods for writing output and generating HTML.
-#
-# Read on for more details.  Examples are provided at the bottom.
-#
-# ## Queries
-#
-# The CGI class dynamically mixes in parameter and cookie-parsing functionality,
-#  environmental variable access, and support for parsing multipart requests
-# (including uploaded files) from the CGI::QueryExtension module.
-#
-# ### Environmental Variables
-#
-# The standard CGI environmental variables are available as read-only attributes
-# of a CGI object.  The following is a list of these variables:
-#
-#     AUTH_TYPE               HTTP_HOST          REMOTE_IDENT
-#     CONTENT_LENGTH          HTTP_NEGOTIATE     REMOTE_USER
-#     CONTENT_TYPE            HTTP_PRAGMA        REQUEST_METHOD
-#     GATEWAY_INTERFACE       HTTP_REFERER       SCRIPT_NAME
-#     HTTP_ACCEPT             HTTP_USER_AGENT    SERVER_NAME
-#     HTTP_ACCEPT_CHARSET     PATH_INFO          SERVER_PORT
-#     HTTP_ACCEPT_ENCODING    PATH_TRANSLATED    SERVER_PROTOCOL
-#     HTTP_ACCEPT_LANGUAGE    QUERY_STRING       SERVER_SOFTWARE
-#     HTTP_CACHE_CONTROL      REMOTE_ADDR
-#     HTTP_FROM               REMOTE_HOST
-#
-# For each of these variables, there is a corresponding attribute with the same
-# name, except all lower case and without a preceding HTTP_. `content_length`
-# and `server_port` are integers; the rest are strings.
-#
-# ### Parameters
-#
-# The method #params() returns a hash of all parameters in the request as
-# name/value-list pairs, where the value-list is an Array of one or more values.
-#  The CGI object itself also behaves as a hash of parameter names to values,
-# but only returns a single value (as a String) for each parameter name.
-#
-# For instance, suppose the request contains the parameter "favourite_colours"
-# with the multiple values "blue" and "green".  The following behavior would
-# occur:
-#
-#     cgi.params["favourite_colours"]  # => ["blue", "green"]
-#     cgi["favourite_colours"]         # => "blue"
-#
-# If a parameter does not exist, the former method will return an empty array,
-# the latter an empty string.  The simplest way to test for existence of a
-# parameter is by the #has_key? method.
-#
-# ### Cookies
-#
-# HTTP Cookies are automatically parsed from the request.  They are available
-# from the #cookies() accessor, which returns a hash from cookie name to
-# CGI::Cookie object.
-#
-# ### Multipart requests
-#
-# If a request's method is POST and its content type is multipart/form-data,
-# then it may contain uploaded files.  These are stored by the QueryExtension
-# module in the parameters of the request.  The parameter name is the name
-# attribute of the file input field, as usual.  However, the value is not a
-# string, but an IO object, either an IOString for small files, or a Tempfile
-# for larger ones.  This object also has the additional singleton methods:
-#
-# #local_path()
-# :   the path of the uploaded file on the local filesystem
-#
-# #original_filename()
-# :   the name of the file on the client computer
-#
-# #content_type()
-# :   the content type of the file
-#
-#
-# ## Responses
-#
-# The CGI class provides methods for sending header and content output to the
-# HTTP client, and mixes in methods for programmatic HTML generation from
-# CGI::HtmlExtension and CGI::TagMaker modules.  The precise version of HTML to
-# use for HTML generation is specified at object creation time.
-#
-# ### Writing output
-#
-# The simplest way to send output to the HTTP client is using the #out() method.
-# This takes the HTTP headers as a hash parameter, and the body content via a
-# block.  The headers can be generated as a string using the #http_header()
-# method.  The output stream can be written directly to using the #print()
-# method.
-#
-# ### Generating HTML
-#
-# Each HTML element has a corresponding method for generating that element as a
-# String.  The name of this method is the same as that of the element, all
-# lowercase.  The attributes of the element are passed in as a hash, and the
-# body as a no-argument block that evaluates to a String.  The HTML generation
-# module knows which elements are always empty, and silently drops any passed-in
-# body.  It also knows which elements require matching closing tags and which
-# don't.  However, it does not know what attributes are legal for which
-# elements.
-#
-# There are also some additional HTML generation methods mixed in from the
-# CGI::HtmlExtension module.  These include individual methods for the different
-# types of form inputs, and methods for elements that commonly take particular
-# attributes where the attributes can be directly specified as arguments, rather
-# than via a hash.
-#
-# ### Utility HTML escape and other methods like a function.
-#
-# There are some utility tool defined in cgi/util.rb . And when include, you can
-# use utility methods like a function.
-#
-# ## Examples of use
-#
-# ### Get form values
-#
-#     require "cgi"
-#     cgi = CGI.new
-#     value = cgi['field_name']   # <== value string for 'field_name'
-#       # if not 'field_name' included, then return "".
-#     fields = cgi.keys            # <== array of field names
-#
-#     # returns true if form has 'field_name'
-#     cgi.has_key?('field_name')
-#     cgi.has_key?('field_name')
-#     cgi.include?('field_name')
-#
-# CAUTION! `cgi['field_name']` returned an Array with the old cgi.rb(included in
-# Ruby 1.6)
-#
-# ### Get form values as hash
-#
-#     require "cgi"
-#     cgi = CGI.new
-#     params = cgi.params
-#
-# cgi.params is a hash.
-#
-#     cgi.params['new_field_name'] = ["value"]  # add new param
-#     cgi.params['field_name'] = ["new_value"]  # change value
-#     cgi.params.delete('field_name')           # delete param
-#     cgi.params.clear                          # delete all params
-#
-# ### Save form values to file
-#
-#     require "pstore"
-#     db = PStore.new("query.db")
-#     db.transaction do
-#       db["params"] = cgi.params
-#     end
-#
-# ### Restore form values from file
-#
-#     require "pstore"
-#     db = PStore.new("query.db")
-#     db.transaction do
-#       cgi.params = db["params"]
-#     end
-#
-# ### Get multipart form values
-#
-#     require "cgi"
-#     cgi = CGI.new
-#     value = cgi['field_name']   # <== value string for 'field_name'
-#     value.read                  # <== body of value
-#     value.local_path            # <== path to local file of value
-#     value.original_filename     # <== original filename of value
-#     value.content_type          # <== content_type of value
-#
-# and value has StringIO or Tempfile class methods.
-#
-# ### Get cookie values
-#
-#     require "cgi"
-#     cgi = CGI.new
-#     values = cgi.cookies['name']  # <== array of 'name'
-#       # if not 'name' included, then return [].
-#     names = cgi.cookies.keys      # <== array of cookie names
-#
-# and cgi.cookies is a hash.
-#
-# ### Get cookie objects
-#
-#     require "cgi"
-#     cgi = CGI.new
-#     for name, cookie in cgi.cookies
-#       cookie.expires = Time.now + 30
-#     end
-#     cgi.out("cookie" => cgi.cookies) {"string"}
-#
-#     cgi.cookies # { "name1" => cookie1, "name2" => cookie2, ... }
-#
-#     require "cgi"
-#     cgi = CGI.new
-#     cgi.cookies['name'].expires = Time.now + 30
-#     cgi.out("cookie" => cgi.cookies['name']) {"string"}
-#
-# ### Print http header and html string to $DEFAULT_OUTPUT ($>)
-#
-#     require "cgi"
-#     cgi = CGI.new("html4")  # add HTML generation methods
-#     cgi.out do
-#       cgi.html do
-#         cgi.head do
-#           cgi.title { "TITLE" }
-#         end +
-#         cgi.body do
-#           cgi.form("ACTION" => "uri") do
-#             cgi.p do
-#               cgi.textarea("get_text") +
-#               cgi.br +
-#               cgi.submit
-#             end
-#           end +
-#           cgi.pre do
-#             CGI.escapeHTML(
-#               "params: #{cgi.params.inspect}\n" +
-#               "cookies: #{cgi.cookies.inspect}\n" +
-#               ENV.collect do |key, value|
-#                 "#{key} --> #{value}\n"
-#               end.join("")
-#             )
-#           end
-#         end
-#       end
-#     end
-#
-#     # add HTML generation methods
-#     CGI.new("html3")    # html3.2
-#     CGI.new("html4")    # html4.01 (Strict)
-#     CGI.new("html4Tr")  # html4.01 Transitional
-#     CGI.new("html4Fr")  # html4.01 Frameset
-#     CGI.new("html5")    # html5
-#
-# ### Some utility methods
-#
-#     require 'cgi/util'
-#     CGI.escapeHTML('Usage: foo "bar" <baz>')
-#
-# ### Some utility methods like a function
-#
-#     require 'cgi/util'
-#     include CGI::Util
-#     escapeHTML('Usage: foo "bar" <baz>')
-#     h('Usage: foo "bar" <baz>') # alias
+# <!-- rdoc-file=lib/cgi/escape.rb -->
+# :stopdoc
 #
 class CGI
   include CGI::Util
@@ -906,66 +637,6 @@ class CGI
                   | (Hash[String, untyped] options_hash) -> void
   end
 
-  module Escape
-    # <!--
-    #   rdoc-file=ext/cgi/escape/escape.c
-    #   - CGI.escape(string) -> string
-    # -->
-    # Returns URL-escaped string (`application/x-www-form-urlencoded`).
-    #
-    def escape: (string str) -> String
-
-    # <!--
-    #   rdoc-file=ext/cgi/escape/escape.c
-    #   - CGI.escapeHTML(string) -> string
-    # -->
-    # Returns HTML-escaped string.
-    #
-    def escapeHTML: (string str) -> String
-
-    # <!--
-    #   rdoc-file=ext/cgi/escape/escape.c
-    #   - CGI.escapeURIComponent(string) -> string
-    # -->
-    # Returns URL-escaped string following RFC 3986.
-    #
-    def escapeURIComponent: (string) -> String
-
-    # <!-- rdoc-file=ext/cgi/escape/escape.c -->
-    # Returns URL-escaped string following RFC 3986.
-    #
-    alias escape_uri_component escapeURIComponent
-
-    # <!--
-    #   rdoc-file=ext/cgi/escape/escape.c
-    #   - CGI.unescape(string, encoding=@@accept_charset) -> string
-    # -->
-    # Returns URL-unescaped string (`application/x-www-form-urlencoded`).
-    #
-    def unescape: (string str, ?encoding encoding) -> String
-
-    # <!--
-    #   rdoc-file=ext/cgi/escape/escape.c
-    #   - CGI.unescapeHTML(string) -> string
-    # -->
-    # Returns HTML-unescaped string.
-    #
-    def unescapeHTML: (string str) -> String
-
-    # <!--
-    #   rdoc-file=ext/cgi/escape/escape.c
-    #   - CGI.unescapeURIComponent(string, encoding=@@accept_charset) -> string
-    # -->
-    # Returns URL-unescaped string following RFC 3986.
-    #
-    def unescapeURIComponent: (string) -> String
-
-    # <!-- rdoc-file=ext/cgi/escape/escape.c -->
-    # Returns URL-unescaped string following RFC 3986.
-    #
-    alias unescape_uri_component unescapeURIComponent
-  end
-
   # <!-- rdoc-file=lib/cgi/core.rb -->
   # Exception raised when there is an invalid encoding detected
   #
@@ -1182,45 +853,6 @@ class CGI
   end
 
   module Util
-    include CGI::Escape
-
-    # <!--
-    #   rdoc-file=lib/cgi/util.rb
-    #   - escapeElement(string, *elements)
-    # -->
-    # Escape only the tags of certain HTML elements in `string`.
-    #
-    # Takes an element or elements or array of elements.  Each element is specified
-    # by the name of the element, without angle brackets. This matches both the
-    # start and the end tag of that element. The attribute list of the open tag will
-    # also be escaped (for instance, the double-quotes surrounding attribute
-    # values).
-    #
-    #     print CGI.escapeElement('<BR><A HREF="url"></A>', "A", "IMG")
-    #       # "<BR>&lt;A HREF=&quot;url&quot;&gt;&lt;/A&gt"
-    #
-    #     print CGI.escapeElement('<BR><A HREF="url"></A>', ["A", "IMG"])
-    #       # "<BR>&lt;A HREF=&quot;url&quot;&gt;&lt;/A&gt"
-    #
-    def escapeElement: (string string, *String | Array[String] elements) -> String
-
-    # <!-- rdoc-file=lib/cgi/util.rb -->
-    # Synonym for CGI.escapeElement(str)
-    #
-    alias escape_element escapeElement
-
-    # <!-- rdoc-file=lib/cgi/util.rb -->
-    # Synonym for CGI.escapeHTML(str)
-    #
-    alias escape_html escapeHTML
-
-    # <!--
-    #   rdoc-file=lib/cgi/util.rb
-    #   - h(string)
-    # -->
-    #
-    alias h escapeHTML
-
     # <!--
     #   rdoc-file=lib/cgi/util.rb
     #   - pretty(string, shift = " ")
@@ -1255,32 +887,6 @@ class CGI
     #
     def rfc1123_date: (Time time) -> String
 
-    # <!--
-    #   rdoc-file=lib/cgi/util.rb
-    #   - unescapeElement(string, *elements)
-    # -->
-    # Undo escaping such as that done by CGI.escapeElement()
-    #
-    #     print CGI.unescapeElement(
-    #             CGI.escapeHTML('<BR><A HREF="url"></A>'), "A", "IMG")
-    #       # "&lt;BR&gt;<A HREF="url"></A>"
-    #
-    #     print CGI.unescapeElement(
-    #             CGI.escapeHTML('<BR><A HREF="url"></A>'), ["A", "IMG"])
-    #       # "&lt;BR&gt;<A HREF="url"></A>"
-    #
-    def unescapeElement: (string string, *String | Array[String] elements) -> String
-
-    # <!-- rdoc-file=lib/cgi/util.rb -->
-    # Synonym for CGI.unescapeElement(str)
-    #
-    alias unescape_element unescapeElement
-
-    # <!-- rdoc-file=lib/cgi/util.rb -->
-    # Synonym for CGI.unescapeHTML(str)
-    #
-    alias unescape_html unescapeHTML
-
     # Abbreviated day-of-week names specified by RFC 822
     RFC822_DAYS: Array[String]
 

data/stdlib/cgi/0/manifest.yaml

@@ -1,3 +1,4 @@
 dependencies:
   - name: tempfile
   - name: stringio
+  - name: cgi-escape