[PATCH v4 2/5] util: Function to parse boolean term queries

[Jani Nikula]

On Mon, 31 Dec 2012, Austin Clements <amdragon at MIT.EDU> wrote:
> This parses the subset of Xapian's boolean term quoting rules that are
> used by make_boolean_term.  This is provided as a generic string
> utility, but will be used shortly in notmuch restore to parse and
> optimize for ID queries.
> ---
>  util/string-util.c |   67 ++++++++++++++++++++++++++++++++++++++++++++++++++++
>  util/string-util.h |   15 ++++++++++++
>  2 files changed, 82 insertions(+)
>
> diff --git a/util/string-util.c b/util/string-util.c
> index e4bea21..52c7781 100644
> --- a/util/string-util.c
> +++ b/util/string-util.c
> @@ -22,6 +22,8 @@
>  #include "string-util.h"
>  #include "talloc.h"
>  
> +#include <ctype.h>
> +
>  char *
>  strtok_len (char *s, const char *delim, size_t *len)
>  {
> @@ -96,3 +98,68 @@ make_boolean_term (void *ctx, const char *prefix, const char *term,
>  
>      return 0;
>  }
> +
> +static const char*
> +skip_space (const char *str)
> +{
> +    while (*str && isspace (*str))

Pedantic: isspace ((unsigned char) *str)

> +	++str;
> +    return str;
> +}
> +
> +int
> +parse_boolean_term (void *ctx, const char *str,
> +		    char **prefix_out, char **term_out)
> +{
> +    *prefix_out = *term_out = NULL;
> +
> +    /* Parse prefix */
> +    str = skip_space (str);
> +    const char *pos = strchr (str, ':');
> +    if (! pos)

if (! pos || pos == str) ?

> +	goto FAIL;

Could just return 1 here.

> +    *prefix_out = talloc_strndup (ctx, str, pos - str);
> +    ++pos;
> +
> +    /* Implement de-quoting compatible with make_boolean_term. */
> +    if (*pos == '"') {
> +	char *out = talloc_array (ctx, char, strlen (pos));
> +	int closed = 0;
> +	*term_out = out;
> +	/* Skip the opening quote, find the closing quote, and
> +	 * un-double doubled internal quotes. */
> +	for (++pos; *pos; ) {
> +	    if (*pos == '"') {
> +		++pos;
> +		if (*pos != '"') {
> +		    /* Found the closing quote. */
> +		    closed = 1;
> +		    pos = skip_space (pos);

Is it necessary to accept trailing space?

> +		    break;
> +		}
> +	    }
> +	    *out++ = *pos++;
> +	}
> +	/* Did the term terminate without a closing quote or is there
> +	 * trailing text after the closing quote? */
> +	if (!closed || *pos)
> +	    goto FAIL;
> +	*out = '\0';
> +    } else {
> +	const char *start = pos;
> +	/* Check for text after the boolean term. */
> +	while (*pos > ' ' && *pos != ')')

The condition could have *pos there too for clarity, though not strictly
necessary. Would be neat to have a ctype style helper that could be
shared between this and make_boolean_term.

> +	    ++pos;
> +	if (*skip_space (pos))

Is it necessary to accept trailing space?

> +	    goto FAIL;
> +	/* No trailing text; dup the string so the caller can free
> +	 * it. */
> +	*term_out = talloc_strndup (ctx, start, pos - start);
> +    }
> +    return 0;
> +
> + FAIL:
> +    talloc_free (*prefix_out);
> +    talloc_free (*term_out);
> +    return 1;
> +}
> diff --git a/util/string-util.h b/util/string-util.h
> index b8844a3..8b9fe50 100644
> --- a/util/string-util.h
> +++ b/util/string-util.h
> @@ -33,4 +33,19 @@ char *strtok_len (char *s, const char *delim, size_t *len);
>  int make_boolean_term (void *talloc_ctx, const char *prefix, const char *term,
>  		       char **buf, size_t *len);
>  
> +/* Parse a boolean term query consisting of a prefix, a colon, and a
> + * term that may be quoted as described for make_boolean_term.  If the
> + * term is not quoted, then it ends at the first whitespace or close
> + * parenthesis.  str may containing leading or trailing whitespace,
> + * but anything else is considered a parse error.  This is compatible
> + * with anything produced by make_boolean_term, and supports a subset
> + * of the quoting styles supported by Xapian (and hence notmuch).
> + * *prefix_out and *term_out will be talloc'd with context ctx.
> + *
> + * Return: 0 on success, non-zero on parse error.
> + */
> +int
> +parse_boolean_term (void *ctx, const char *str,
> +		    char **prefix_out, char **term_out);
> +
>  #endif
> -- 
> 1.7.10.4