Changeset 181

Timestamp:

05/30/06 13:49:18 (2 years ago)

Author:

xi

Message:

Complete UTF-8 and UTF-16 decoders.

Reader is mostly done (though untested).

Files:

• libyaml/trunk/include/yaml/yaml.h (modified) (3 diffs)
• libyaml/trunk/src/reader.c (modified) (9 diffs)
• libyaml/trunk/tests/Makefile.am (modified) (1 diff)
• libyaml/trunk/tests/test-reader.c (copied) (copied from libyaml/trunk/tests/test-version.c) (1 diff)

libyaml/trunk/include/yaml/yaml.h

@@ -292 +292 @@
-     */
-
+    /** Error type. */
-    yaml_error_type_t error;
+
+    /** Error description. */
+    const char *problem;
+
+    /** The byte about which the problem occured. */
+    size_t problem_offset;
-
-    /**
@@ -303 +310 @@
-     */
-
-
+.
-    yaml_read_handler_t *read_handler;
-
@@ -489 +496 @@
-#define YAML_BUFFER_SIZE    (YAML_RAW_BUFFER_SIZE*3)
-
+/**
+ * Ensure that the buffer contains at least @a length characters.
+ *
+ * @param[in]   parser  A parser object.
+ * @param[in]   length  The number of characters in the buffer.
+ *
+ * @returns @c 1 on success, @c 0 on error.
+ */
+
+int
+yaml_parser_update_buffer(yaml_parser_t *parser, size_t length);
+
-/** @} */
-

libyaml/trunk/src/reader.c

@@ -8 +8 @@
-#include <assert.h>
-
-/* Check for the UTF-16-BE BOM. */
-#define IS_UTF16BE_BOM(pointer) ((pointer)[0] == 0xFE && (pointer)[1] == 0xFF)
-
-/* Check for the UTF-16-LE BOM. */
-#define IS_UTF16LE_BOM(pointer) ((pointer)[0] == 0xFF && (pointer)[1] == 0xFE)
-
-/* Get a UTF-16-BE character. */
-#define UTF16BE_CHAR(pointer)   ((pointer)[0] << 8 + (pointer)[1])
-
-/* Get a UTF-16-LE character. */
-#define UTF16LE_CHAR(pointer)   ((pointer)[0] + (pointer)[1] << 8)
-
-/*
-
-
-
-
-
-
-
-
-
+
- */
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
+
+
+
+
+
+
+
+
+
+
-
-/*
@@ -103 +72 @@
-        if (!yaml_parser_update_raw_buffer(parser)) return 0;
-
+        /* If the raw buffer is empty, it is EOF. */
+
+        if (!parser->raw_unread) return 1;
+
-        /* Decode the raw buffer. */
-
-        while (parser->raw_unread)
-        {
-ch
+value, value2
-            int incomplete = 0;
+            unsigned char utf8_octet;
+            unsigned int utf8_length;
+            int k, low, high;
-
-            /* Decode the next character. */
@@ -116 +92 @@
-                case YAML_UTF8_ENCODING:
-
-
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
-
-                    /* Check if the raw buffer contains an incomplete character. */
@@ -123 +131 @@
-                    if (utf8_length > parser->raw_unread) {
-                        if (parser->eof) {
-parser->error = YAML_READER_ERROR;
-return 0
+return yaml_parser_set_reader_error(parser,
+        "Incomplete UTF-8 octet sequence")
-                        }
-                        incomplete = 1;
+                        break;
-                    }
-
-
-
-
-
-
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
-                    }
-
-
-
-
-
-
-
-
-
-
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
-
-                    break;
-                
-                case YAML_UTF16LE_ENCODING:
-
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
-
-                    if (parser->raw_unread < 2) {
-                        if (parser->eof) {
-parser->error = YAML_READER_ERROR;
-return 0
+return yaml_parser_set_reader_error(parser,
+        "Incomplete UTF-16 character")
-                        }
-                        incomplete = 1;
+                        break;
-                    }
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
-                        }
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
-                    }
-
-/* Get the current character. */
-
-ch = UTF16BE_CHAR(parser->raw_pointer)
-parser->raw_pointer += 2
-parser->raw_unread -= 2;
+else {
+
+    parser->raw_unread -= 2
+    parser->offset += 4
+}
-
-                    break;
-            }
+
+            /* Check if the raw buffer contains enough bytes to form a character. */
+
+            if (incomplete) break;
-
-            /*
@@ -198 +293 @@
-             */
-
-
-
-
-
-
-
-
-
+
+
+
+
+
+
+
-
-            /* Finally put the character into the buffer. */
-
-            /* 0000 0000-0000 007F -> 0xxxxxxx */
-ch
-ch
+value
+value
-            }
-            /* 0000 0080-0000 07FF -> 110xxxxx 10xxxxxx */
-ch
-ch >> 6) & 0x1F
-ch
+value
+value >> 6)
+value
-            }
-            /* 0000 0800-0000 FFFF -> 1110xxxx 10xxxxxx 10xxxxxx */
-ch
-80 + ch & 0x3F
-C0 + (ch >> 6) & 0x1
-
+value
+E0 + (value >> 12)
+80 + (value >> 6) & 0x3
+*(parser->buffer_end++) = 0x80 + value & 0x3F;
-            }
-            /* 0001 0000-0010 FFFF -> 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx */
-            else {
+                *(parser->buffer_end++) = 0xF0 + (value >> 18);
+                *(parser->buffer_end++) = 0x80 + (value >> 12) & 0x3F;
+                *(parser->buffer_end++) = 0x80 + (value >> 6) & 0x3F;
+                *(parser->buffer_end++) = 0x80 + value & 0x3F;
-            }
-        }
-    
-
-
+}
+
+
-}
-
@@ -238 +336 @@
- */
-
+#define BOM_UTF8    "\xef\xbb\xbf"
+#define BOM_UTF16LE "\xff\xfe"
+#define BOM_UTF16BE "\xfe\xff"
+
-int
-yaml_parser_determine_encoding(yaml_parser_t *parser)
@@ -243 +345 @@
-    /* Ensure that we had enough bytes in the raw buffer. */
-
-2
+3
-        if (!yaml_parser_update_raw_buffer(parser)) {
-            return 0;
@@ -251 +353 @@
-    /* Determine the encoding. */
-
-
+
+
+
+
+
+
+
+
-        parser->encoding = YAML_UTF16BE_ENCODING;
-
-
-
+
+
+
+
+
+
+
+
-    }
-    else {
-        parser->encoding = YAML_UTF8_ENCODING;
-    }
+
+    return 1;
-}
-
@@ -292 +408 @@
-                YAML_RAW_BUFFER_SIZE - parser->raw_unread,
-                &size_read)) {
-
-
+
-    }
-    parser->raw_unread += size_read;

libyaml/trunk/tests/Makefile.am

@@ -1 +1 @@
-AM_CPPFLAGS = -I$(top_srcdir)/include
-LDADD = $(top_builddir)/src/libyaml.la
-
-
+ test-reader
+ test-reader

libyaml/trunk/tests/test-reader.c

@@ -5 +5 @@
-#include <assert.h>
-
+/*
+ * Test cases are stolen from
+ * http://www.cl.cam.ac.uk/~mgk25/ucs/examples/UTF-8-test.txt
+ */
+
+typedef struct {
+    char *title;
+    char *test;
+    int result;
+} test_case;
+
+test_case utf8_sequences[] = {
+        /* {"title", "test 1|test 2|...|test N!", (0 or 1)}, */
+
+        {"a simple test", "'test' is '\xd0\xbf\xd1\x80\xd0\xbe\xd0\xb2\xd0\xb5\xd1\x80\xd0\xba\xd0\xb0' in Russian!", 1},
+        {"an empty line", "!", 1},
+
+        {"u-0 is a control character", "\x00!", 0},
+        {"u-80 is a control character", "\xc2\x80!", 0},
+        {"u-800 is valid", "\xe0\xa0\x80!", 1},
+        {"u-10000 is valid", "\xf0\x90\x80\x80!", 1},
+        {"5 bytes sequences are not allowed", "\xf8\x88\x80\x80\x80!", 0},
+        {"6 bytes sequences are not allowed", "\xfc\x84\x80\x80\x80\x80!", 0},
+
+        {"u-7f is a control character", "\x7f!", 0},
+        {"u-7FF is valid", "\xdf\xbf!", 1},
+        {"u-FFFF is a control character", "\xef\xbf\xbf!", 0},
+        {"u-1FFFFF is too large", "\xf7\xbf\xbf\xbf!", 0},
+        {"u-3FFFFFF is 5 bytes", "\xfb\xbf\xbf\xbf\xbf!", 0},
+        {"u-7FFFFFFF is 6 bytes", "\xfd\xbf\xbf\xbf\xbf\xbf!", 0},
+
+        {"u-D7FF", "\xed\x9f\xbf!", 1},
+        {"u-E000", "\xee\x80\x80!", 1},
+        {"u-FFFD", "\xef\xbf\xbd!", 1},
+        {"u-10FFFF", "\xf4\x8f\xbf\xbf!", 1},
+        {"u-110000", "\xf4\x90\x80\x80!", 0},
+
+        {"first continuation byte", "\x80!", 0},
+        {"last continuation byte", "\xbf!", 0},
+
+        {"2 continuation bytes", "\x80\xbf!", 0},
+        {"3 continuation bytes", "\x80\xbf\x80!", 0},
+        {"4 continuation bytes", "\x80\xbf\x80\xbf!", 0},
+        {"5 continuation bytes", "\x80\xbf\x80\xbf\x80!", 0},
+        {"6 continuation bytes", "\x80\xbf\x80\xbf\x80\xbf!", 0},
+        {"7 continuation bytes", "\x80\xbf\x80\xbf\x80\xbf\x80!", 0},
+
+        {"sequence of all 64 possible continuation bytes",
+         "\x80|\x81|\x82|\x83|\x84|\x85|\x86|\x87|\x88|\x89|\x8a|\x8b|\x8c|\x8d|\x8e|\x8f|"
+         "\x90|\x91|\x92|\x93|\x94|\x95|\x96|\x97|\x98|\x99|\x9a|\x9b|\x9c|\x9d|\x9e|\x9f|"
+         "\xa0|\xa1|\xa2|\xa3|\xa4|\xa5|\xa6|\xa7|\xa8|\xa9|\xaa|\xab|\xac|\xad|\xae|\xaf|"
+         "\xb0|\xb1|\xb2|\xb3|\xb4|\xb5|\xb6|\xb7|\xb8|\xb9|\xba|\xbb|\xbc|\xbd|\xbe|\xbf!", 0},
+        {"32 first bytes of 2-byte sequences {0xc0-0xdf}",
+         "\xc0 |\xc1 |\xc2 |\xc3 |\xc4 |\xc5 |\xc6 |\xc7 |\xc8 |\xc9 |\xca |\xcb |\xcc |\xcd |\xce |\xcf |"
+         "\xd0 |\xd1 |\xd2 |\xd3 |\xd4 |\xd5 |\xd6 |\xd7 |\xd8 |\xd9 |\xda |\xdb |\xdc |\xdd |\xde |\xdf !", 0},
+        {"16 first bytes of 3-byte sequences {0xe0-0xef}",
+         "\xe0 |\xe1 |\xe2 |\xe3 |\xe4 |\xe5 |\xe6 |\xe7 |\xe8 |\xe9 |\xea |\xeb |\xec |\xed |\xee |\xef !", 0},
+        {"8 first bytes of 4-byte sequences {0xf0-0xf7}", "\xf0 |\xf1 |\xf2 |\xf3 |\xf4 |\xf5 |\xf6 |\xf7 !", 0},
+        {"4 first bytes of 5-byte sequences {0xf8-0xfb}", "\xf8 |\xf9 |\xfa |\xfb !", 0},
+        {"2 first bytes of 6-byte sequences {0xfc-0xfd}", "\xfc |\xfd !", 0},
+
+        {"sequences with last byte missing {u-0}",
+         "\xc0|\xe0\x80|\xf0\x80\x80|\xf8\x80\x80\x80|\xfc\x80\x80\x80\x80!", 0},
+        {"sequences with last byte missing {u-...FF}",
+         "\xdf|\xef\xbf|\xf7\xbf\xbf|\xfb\xbf\xbf\xbf|\xfd\xbf\xbf\xbf\xbf!", 0},
+
+        {"impossible bytes", "\xfe|\xff|\xfe\xfe\xff\xff!", 0},
+
+        {"overlong sequences {u-2f}",
+         "\xc0\xaf|\xe0\x80\xaf|\xf0\x80\x80\xaf|\xf8\x80\x80\x80\xaf|\xfc\x80\x80\x80\x80\xaf!", 0},
+
+        {"maximum overlong sequences",
+         "\xc1\xbf|\xe0\x9f\xbf|\xf0\x8f\xbf\xbf|\xf8\x87\xbf\xbf\xbf|\xfc\x83\xbf\xbf\xbf\xbf!", 0},
+
+        {"overlong representation of the NUL character",
+         "\xc0\x80|\xe0\x80\x80|\xf0\x80\x80\x80|\xf8\x80\x80\x80\x80|\xfc\x80\x80\x80\x80\x80!", 0},
+
+        {"single UTF-16 surrogates",
+         "\xed\xa0\x80|\xed\xad\xbf|\xed\xae\x80|\xed\xaf\xbf|\xed\xb0\x80|\xed\xbe\x80|\xed\xbf\xbf!", 0},
+
+        {"paired UTF-16 surrogates",
+         "\xed\xa0\x80\xed\xb0\x80|\xed\xa0\x80\xed\xbf\xbf|\xed\xad\xbf\xed\xb0\x80|"
+         "\xed\xad\xbf\xed\xbf\xbf|\xed\xae\x80\xed\xb0\x80|\xed\xae\x80\xed\xbf\xbf|"
+         "\xed\xaf\xbf\xed\xb0\x80|\xed\xaf\xbf\xed\xbf\xbf!", 0},
+
+        {"other illegal code positions", "\xef\xbf\xbe|\xef\xbf\xbf!", 0},
+
+        {NULL, NULL, 0}
+};
+
+int check_utf8_sequences(void)
+{
+    yaml_parser_t *parser;
+    int failed = 0;
+    int k;
+    printf("checking utf-8 sequences...\n");
+    for (k = 0; utf8_sequences[k].test; k++) {
+        char *title = utf8_sequences[k].title;
+        int check = utf8_sequences[k].result;
+        int result;
+        char *start = utf8_sequences[k].test;
+        char *end = start;
+        printf("\t%s:\n", title);
+        while(1) {
+            while (*end != '|' && *end != '!') end++;
+            parser = yaml_parser_new();
+            assert(parser);
+            yaml_parser_set_input_string(parser, (unsigned char *)start, end-start);
+            result = yaml_parser_update_buffer(parser, end-start);
+            if (result != check) {
+                printf("\t\t- ");
+                failed ++;
+            }
+            else {
+                printf("\t\t+ ");
+            }
+            if (!parser->error) {
+                printf("(no error)\n");
+            }
+            else if (parser->error == YAML_READER_ERROR) {
+                printf("(reader error: %s at %d)\n", parser->problem, parser->problem_offset);
+            }
+            if (*end == '!') break;
+            start = ++end;
+            yaml_parser_delete(parser);
+        };
+        printf("\n");
+    }
+    printf("checking utf-8 sequences: %d fail(s)\n", failed);
+    return failed;
+}
+
+
-int
-main(void)
-{
-
-
-
-
-
-
-
-
-
-
+
-}