option_parser.c: Allow comments on lines with quoted strings.

The current behavior is
 - If the value contains a double-quote:
   - 1. Verify that it must contains at least two quotes.
   - 2. If one of the quotes is the first character, trim it.
   - 3. If one of the quotes is the last character, trim it.
 - Else:
   - 1. Trim a trailing comment from the value.

This has the effect that

    `key = "value" # comment` => `value" #comment`

This is surprising and almost certainly not what the user wants.

However, it allows simple nested quotes like:

    `key = "A string "with quotes""` => `A string "with quotes"`

Fix the brokenness of the first example at the expense of breaking the
second.  A user seeking that value will now have to type:

    key = "A string \"with quotes\""

Do this by treating double-quote as a toggle that simply changes whether
`;` and `#` start comments (not too different than Bash using it to toggle
field separation).

In order to have strings that contain a literal double-quote, add
rudimentary support for backslash-escaping.  For now, only recognize
double-quote and backslash-itself; anything else is undefined; and the
program is free to do whatever it likes with them; for now, silently treat
the backslash as an ordinary character.

Note that this formulation of quoting implies that backslash-escaping works
identically both inside and outside of quotes.

src/option_parser.c

@@ -29,7 +29,7 @@ static section_t *new_section(char *name);
 static section_t *get_section(char *name);
 static void add_entry(char *section_name, char *key, char *value);
 static char *get_value(char *section, char *key);
-static char *clean_value(char *value);
+static char *clean_value(char *value, int line_num);
 
 static int cmdline_argc;
 static char **cmdline_argv;
@@ -91,7 +91,7 @@ void add_entry(char *section_name, char *key, char *value)
         int len = s->entry_count;
         s->entries = g_realloc(s->entries, sizeof(entry_t) * len);
         s->entries[s->entry_count - 1].key = g_strdup(key);
-        s->entries[s->entry_count - 1].value = clean_value(value);
+        s->entries[s->entry_count - 1].value = g_strdup(value);
 }
 
 char *get_value(char *section, char *key)
@@ -186,20 +186,50 @@ int ini_get_bool(char *section, char *key, int def)
         }
 }
 
-char *clean_value(char *value)
+char *clean_value(char *value, int line_num)
 {
-        char *s;
+        char *unparsed = value;
 
-        if (value[0] == '"')
+        bool in_quote = false;
-                s = g_strdup(value + 1);
+        while ((unparsed = strpbrk(unparsed, "\"\\#;")) != NULL) {
+                switch (*unparsed) {
+                case '"':
+                        memmove(unparsed, unparsed + 1, strlen(unparsed));
+                        in_quote = !in_quote;
+                        break;
+                case '\\':
+                        switch (unparsed[1]) {
+                        case '\\':
+                        case '"':
+                                memmove(unparsed, unparsed + 1, strlen(unparsed));
+                                unparsed++;
+                                break;
+                        default:
+                                // Unrecognized backslash sequence;
+                                // treat the backslash as an ordinary character.
+                                // Consider issuing an error or warning here instead.
+                                unparsed++;
+                                break;
+                        }
+                        break;
+                case '#':
+                case ';':
+                        if (in_quote)
+                                unparsed++;
                         else
-                s = g_strdup(value);
+                                *unparsed = '\0';
-
+                        break;
-        if (s[strlen(s) - 1] == '"')
+                }
-                s[strlen(s) - 1] = '\0';
+        }
-
+        if (in_quote) {
-        return s;
+                fprintf(stderr,
+                       "Warning: invalid config file at line %d\n",
+                       line_num);
+                fprintf(stderr, "Missing '\"'\n");
+                return NULL;
+        }
 
+        return g_strstrip(value);
 }
 
 int load_ini_file(FILE * fp)
@@ -250,24 +280,8 @@ int load_ini_file(FILE * fp)
 
                 *equal = '\0';
                 char *key = g_strstrip(start);
-                char *value = g_strstrip(equal + 1);
+                char *value = clean_value(equal + 1, line_num);
-
+                if (!value) continue;
-                char *quote = strchr(value, '"');
-                if (quote) {
-                        char *closing_quote = strchr(quote + 1, '"');
-                        if (!closing_quote) {
-                                fprintf(stderr,
-                                     "Warning: invalid config file at line %d\n",
-                                     line_num);
-                                fprintf(stderr, "Missing '\"'\n");
-                                continue;
-                        }
-                } else {
-                        char *comment = strpbrk(value, "#;");
-                        if (comment)
-                                *comment = '\0';
-                }
-                value = g_strstrip(value);
 
                 if (!current_section) {
                         fprintf(stderr,

test/data/test-ini

@@ -20,8 +20,16 @@
 
 [string]
 	simple = A simple string
+	simple_with_hcomment = A simple string # a comment
+	simple_with_scomment = A simple string ; a comment
 	quoted = "A quoted string"
-	quoted_with_quotes = "A string "with quotes""
+	quoted_with_hcomment = "A quoted string" # a comment
+	quoted_with_scomment = "A quoted string" ; a comment
+	quoted_with_quotes = "A string \"with quotes\""
+	quoted_with_escapes = "A string \\\"with escapes\\"
+	quoted_with_cchar = "A string; with #comment characters" # a comment
+	quoted_in_middle  = A string"; with #comment" characters # a comment
+	escaped_quotes = String \"with quotes\"
 
 [int]
 	simple = 5

test/option_parser.c

@@ -45,13 +45,31 @@ TEST test_ini_get_string(void)
 {
         char *string_section = "string";
         char *ptr;
+
         ASSERT_STR_EQ("A simple string", (ptr = ini_get_string(string_section, "simple", "")));
         free(ptr);
+        ASSERT_STR_EQ("A simple string", (ptr = ini_get_string(string_section, "simple_with_hcomment", "")));
+        free(ptr);
+        ASSERT_STR_EQ("A simple string", (ptr = ini_get_string(string_section, "simple_with_scomment", "")));
+        free(ptr);
 
         ASSERT_STR_EQ("A quoted string", (ptr = ini_get_string(string_section, "quoted", "")));
         free(ptr);
+        ASSERT_STR_EQ("A quoted string", (ptr = ini_get_string(string_section, "quoted_with_hcomment", "")));
+        free(ptr);
+        ASSERT_STR_EQ("A quoted string", (ptr = ini_get_string(string_section, "quoted_with_scomment", "")));
+        free(ptr);
         ASSERT_STR_EQ("A string \"with quotes\"", (ptr = ini_get_string(string_section, "quoted_with_quotes", "")));
         free(ptr);
+        ASSERT_STR_EQ("A string \\\"with escapes\\", (ptr = ini_get_string(string_section, "quoted_with_escapes", "")));
+        free(ptr);
+        ASSERT_STR_EQ("A string; with #comment characters", (ptr = ini_get_string(string_section, "quoted_with_cchar", "")));
+        free(ptr);
+        ASSERT_STR_EQ("A string; with #comment characters", (ptr = ini_get_string(string_section, "quoted_in_middle", "")));
+        free(ptr);
+
+        ASSERT_STR_EQ("String \"with quotes\"", (ptr = ini_get_string(string_section, "escaped_quotes", "")));
+        free(ptr);
 
         ASSERT_STR_EQ("default value", (ptr = ini_get_string(string_section, "nonexistent", "default value")));
         free(ptr);