ed-precompiled_prism 1.5.2

data/src/util/pm_strpbrk.c

@@ -0,0 +1,206 @@
+#include "prism/util/pm_strpbrk.h"
+
+/**
+ * Add an invalid multibyte character error to the parser.
+ */
+static inline void
+pm_strpbrk_invalid_multibyte_character(pm_parser_t *parser, const uint8_t *start, const uint8_t *end) {
+    pm_diagnostic_list_append_format(&parser->error_list, start, end, PM_ERR_INVALID_MULTIBYTE_CHARACTER, *start);
+}
+
+/**
+ * Set the explicit encoding for the parser to the current encoding.
+ */
+static inline void
+pm_strpbrk_explicit_encoding_set(pm_parser_t *parser, const uint8_t *source, size_t width) {
+    if (parser->explicit_encoding != NULL) {
+        if (parser->explicit_encoding == parser->encoding) {
+            // Okay, we already locked to this encoding.
+        } else if (parser->explicit_encoding == PM_ENCODING_UTF_8_ENTRY) {
+            // Not okay, we already found a Unicode escape sequence and this
+            // conflicts.
+            pm_diagnostic_list_append_format(&parser->error_list, source, source + width, PM_ERR_MIXED_ENCODING, parser->encoding->name);
+        } else {
+            // Should not be anything else.
+            assert(false && "unreachable");
+        }
+    }
+
+    parser->explicit_encoding = parser->encoding;
+}
+
+/**
+ * This is the default path.
+ */
+static inline const uint8_t *
+pm_strpbrk_utf8(pm_parser_t *parser, const uint8_t *source, const uint8_t *charset, size_t maximum, bool validate) {
+    size_t index = 0;
+
+    while (index < maximum) {
+        if (strchr((const char *) charset, source[index]) != NULL) {
+            return source + index;
+        }
+
+        if (source[index] < 0x80) {
+            index++;
+        } else {
+            size_t width = pm_encoding_utf_8_char_width(source + index, (ptrdiff_t) (maximum - index));
+
+            if (width > 0) {
+                index += width;
+            } else if (!validate) {
+                index++;
+            } else {
+                // At this point we know we have an invalid multibyte character.
+                // We'll walk forward as far as we can until we find the next
+                // valid character so that we don't spam the user with a ton of
+                // the same kind of error.
+                const size_t start = index;
+
+                do {
+                    index++;
+                } while (index < maximum && pm_encoding_utf_8_char_width(source + index, (ptrdiff_t) (maximum - index)) == 0);
+
+                pm_strpbrk_invalid_multibyte_character(parser, source + start, source + index);
+            }
+        }
+    }
+
+    return NULL;
+}
+
+/**
+ * This is the path when the encoding is ASCII-8BIT.
+ */
+static inline const uint8_t *
+pm_strpbrk_ascii_8bit(pm_parser_t *parser, const uint8_t *source, const uint8_t *charset, size_t maximum, bool validate) {
+    size_t index = 0;
+
+    while (index < maximum) {
+        if (strchr((const char *) charset, source[index]) != NULL) {
+            return source + index;
+        }
+
+        if (validate && source[index] >= 0x80) pm_strpbrk_explicit_encoding_set(parser, source, 1);
+        index++;
+    }
+
+    return NULL;
+}
+
+/**
+ * This is the slow path that does care about the encoding.
+ */
+static inline const uint8_t *
+pm_strpbrk_multi_byte(pm_parser_t *parser, const uint8_t *source, const uint8_t *charset, size_t maximum, bool validate) {
+    size_t index = 0;
+    const pm_encoding_t *encoding = parser->encoding;
+
+    while (index < maximum) {
+        if (strchr((const char *) charset, source[index]) != NULL) {
+            return source + index;
+        }
+
+        if (source[index] < 0x80) {
+            index++;
+        } else {
+            size_t width = encoding->char_width(source + index, (ptrdiff_t) (maximum - index));
+            if (validate) pm_strpbrk_explicit_encoding_set(parser, source, width);
+
+            if (width > 0) {
+                index += width;
+            } else if (!validate) {
+                index++;
+            } else {
+                // At this point we know we have an invalid multibyte character.
+                // We'll walk forward as far as we can until we find the next
+                // valid character so that we don't spam the user with a ton of
+                // the same kind of error.
+                const size_t start = index;
+
+                do {
+                    index++;
+                } while (index < maximum && encoding->char_width(source + index, (ptrdiff_t) (maximum - index)) == 0);
+
+                pm_strpbrk_invalid_multibyte_character(parser, source + start, source + index);
+            }
+        }
+    }
+
+    return NULL;
+}
+
+/**
+ * This is the fast path that does not care about the encoding because we know
+ * the encoding only supports single-byte characters.
+ */
+static inline const uint8_t *
+pm_strpbrk_single_byte(pm_parser_t *parser, const uint8_t *source, const uint8_t *charset, size_t maximum, bool validate) {
+    size_t index = 0;
+    const pm_encoding_t *encoding = parser->encoding;
+
+    while (index < maximum) {
+        if (strchr((const char *) charset, source[index]) != NULL) {
+            return source + index;
+        }
+
+        if (source[index] < 0x80 || !validate) {
+            index++;
+        } else {
+            size_t width = encoding->char_width(source + index, (ptrdiff_t) (maximum - index));
+            pm_strpbrk_explicit_encoding_set(parser, source, width);
+
+            if (width > 0) {
+                index += width;
+            } else {
+                // At this point we know we have an invalid multibyte character.
+                // We'll walk forward as far as we can until we find the next
+                // valid character so that we don't spam the user with a ton of
+                // the same kind of error.
+                const size_t start = index;
+
+                do {
+                    index++;
+                } while (index < maximum && encoding->char_width(source + index, (ptrdiff_t) (maximum - index)) == 0);
+
+                pm_strpbrk_invalid_multibyte_character(parser, source + start, source + index);
+            }
+        }
+    }
+
+    return NULL;
+}
+
+/**
+ * Here we have rolled our own version of strpbrk. The standard library strpbrk
+ * has undefined behavior when the source string is not null-terminated. We want
+ * to support strings that are not null-terminated because pm_parse does not
+ * have the contract that the string is null-terminated. (This is desirable
+ * because it means the extension can call pm_parse with the result of a call to
+ * mmap).
+ *
+ * The standard library strpbrk also does not support passing a maximum length
+ * to search. We want to support this for the reason mentioned above, but we
+ * also don't want it to stop on null bytes. Ruby actually allows null bytes
+ * within strings, comments, regular expressions, etc. So we need to be able to
+ * skip past them.
+ *
+ * Finally, we want to support encodings wherein the charset could contain
+ * characters that are trailing bytes of multi-byte characters. For example, in
+ * Shift_JIS, the backslash character can be a trailing byte. In that case we
+ * need to take a slower path and iterate one multi-byte character at a time.
+ */
+const uint8_t *
+pm_strpbrk(pm_parser_t *parser, const uint8_t *source, const uint8_t *charset, ptrdiff_t length, bool validate) {
+    if (length <= 0) {
+        return NULL;
+    } else if (!parser->encoding_changed) {
+        return pm_strpbrk_utf8(parser, source, charset, (size_t) length, validate);
+    } else if (parser->encoding == PM_ENCODING_ASCII_8BIT_ENTRY) {
+        return pm_strpbrk_ascii_8bit(parser, source, charset, (size_t) length, validate);
+    } else if (parser->encoding->multibyte) {
+        return pm_strpbrk_multi_byte(parser, source, charset, (size_t) length, validate);
+    } else {
+        return pm_strpbrk_single_byte(parser, source, charset, (size_t) length, validate);
+    }
+}

metadata

@@ -0,0 +1,195 @@
+--- !ruby/object:Gem::Specification
+name: ed-precompiled_prism
+version: !ruby/object:Gem::Version
+  version: 1.5.2
+platform: ruby
+authors:
+- Shopify
+bindir: bin
+cert_chain: []
+date: 1980-01-02 00:00:00.000000000 Z
+dependencies: []
+email:
+- ruby@shopify.com
+executables: []
+extensions:
+- ext/prism/extconf.rb
+extra_rdoc_files: []
+files:
+- BSDmakefile
+- CHANGELOG.md
+- CODE_OF_CONDUCT.md
+- CONTRIBUTING.md
+- LICENSE.md
+- Makefile
+- README.md
+- config.yml
+- docs/build_system.md
+- docs/configuration.md
+- docs/cruby_compilation.md
+- docs/design.md
+- docs/encoding.md
+- docs/fuzzing.md
+- docs/heredocs.md
+- docs/javascript.md
+- docs/local_variable_depth.md
+- docs/mapping.md
+- docs/parser_translation.md
+- docs/parsing_rules.md
+- docs/releasing.md
+- docs/relocation.md
+- docs/ripper_translation.md
+- docs/ruby_api.md
+- docs/ruby_parser_translation.md
+- docs/serialization.md
+- docs/testing.md
+- ext/prism/api_node.c
+- ext/prism/api_pack.c
+- ext/prism/extconf.rb
+- ext/prism/extension.c
+- ext/prism/extension.h
+- include/prism.h
+- include/prism/ast.h
+- include/prism/defines.h
+- include/prism/diagnostic.h
+- include/prism/encoding.h
+- include/prism/node.h
+- include/prism/options.h
+- include/prism/pack.h
+- include/prism/parser.h
+- include/prism/prettyprint.h
+- include/prism/regexp.h
+- include/prism/static_literals.h
+- include/prism/util/pm_buffer.h
+- include/prism/util/pm_char.h
+- include/prism/util/pm_constant_pool.h
+- include/prism/util/pm_integer.h
+- include/prism/util/pm_list.h
+- include/prism/util/pm_memchr.h
+- include/prism/util/pm_newline_list.h
+- include/prism/util/pm_string.h
+- include/prism/util/pm_strncasecmp.h
+- include/prism/util/pm_strpbrk.h
+- include/prism/version.h
+- lib/prism.rb
+- lib/prism/compiler.rb
+- lib/prism/desugar_compiler.rb
+- lib/prism/dispatcher.rb
+- lib/prism/dot_visitor.rb
+- lib/prism/dsl.rb
+- lib/prism/ffi.rb
+- lib/prism/inspect_visitor.rb
+- lib/prism/lex_compat.rb
+- lib/prism/mutation_compiler.rb
+- lib/prism/node.rb
+- lib/prism/node_ext.rb
+- lib/prism/pack.rb
+- lib/prism/parse_result.rb
+- lib/prism/parse_result/comments.rb
+- lib/prism/parse_result/errors.rb
+- lib/prism/parse_result/newlines.rb
+- lib/prism/pattern.rb
+- lib/prism/polyfill/append_as_bytes.rb
+- lib/prism/polyfill/byteindex.rb
+- lib/prism/polyfill/scan_byte.rb
+- lib/prism/polyfill/unpack1.rb
+- lib/prism/polyfill/warn.rb
+- lib/prism/reflection.rb
+- lib/prism/relocation.rb
+- lib/prism/serialize.rb
+- lib/prism/string_query.rb
+- lib/prism/translation.rb
+- lib/prism/translation/parser.rb
+- lib/prism/translation/parser/builder.rb
+- lib/prism/translation/parser/compiler.rb
+- lib/prism/translation/parser/lexer.rb
+- lib/prism/translation/parser33.rb
+- lib/prism/translation/parser34.rb
+- lib/prism/translation/parser35.rb
+- lib/prism/translation/parser_current.rb
+- lib/prism/translation/ripper.rb
+- lib/prism/translation/ripper/sexp.rb
+- lib/prism/translation/ripper/shim.rb
+- lib/prism/translation/ruby_parser.rb
+- lib/prism/visitor.rb
+- prism.gemspec
+- rbi/prism.rbi
+- rbi/prism/compiler.rbi
+- rbi/prism/dsl.rbi
+- rbi/prism/inspect_visitor.rbi
+- rbi/prism/node.rbi
+- rbi/prism/node_ext.rbi
+- rbi/prism/parse_result.rbi
+- rbi/prism/reflection.rbi
+- rbi/prism/string_query.rbi
+- rbi/prism/translation/parser.rbi
+- rbi/prism/translation/parser33.rbi
+- rbi/prism/translation/parser34.rbi
+- rbi/prism/translation/parser35.rbi
+- rbi/prism/translation/ripper.rbi
+- rbi/prism/visitor.rbi
+- sig/prism.rbs
+- sig/prism/compiler.rbs
+- sig/prism/dispatcher.rbs
+- sig/prism/dot_visitor.rbs
+- sig/prism/dsl.rbs
+- sig/prism/inspect_visitor.rbs
+- sig/prism/lex_compat.rbs
+- sig/prism/mutation_compiler.rbs
+- sig/prism/node.rbs
+- sig/prism/node_ext.rbs
+- sig/prism/pack.rbs
+- sig/prism/parse_result.rbs
+- sig/prism/parse_result/comments.rbs
+- sig/prism/pattern.rbs
+- sig/prism/reflection.rbs
+- sig/prism/relocation.rbs
+- sig/prism/serialize.rbs
+- sig/prism/string_query.rbs
+- sig/prism/visitor.rbs
+- src/diagnostic.c
+- src/encoding.c
+- src/node.c
+- src/options.c
+- src/pack.c
+- src/prettyprint.c
+- src/prism.c
+- src/regexp.c
+- src/serialize.c
+- src/static_literals.c
+- src/token_type.c
+- src/util/pm_buffer.c
+- src/util/pm_char.c
+- src/util/pm_constant_pool.c
+- src/util/pm_integer.c
+- src/util/pm_list.c
+- src/util/pm_memchr.c
+- src/util/pm_newline_list.c
+- src/util/pm_string.c
+- src/util/pm_strncasecmp.c
+- src/util/pm_strpbrk.c
+homepage: https://github.com/ruby/prism
+licenses:
+- MIT
+metadata:
+  allowed_push_host: https://rubygems.org
+  source_code_uri: https://github.com/ruby/prism
+  changelog_uri: https://github.com/ruby/prism/blob/main/CHANGELOG.md
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: 2.7.0
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubygems_version: 3.6.7
+specification_version: 4
+summary: Prism Ruby parser
+test_files: []