X-Git-Url: https://git.notmuchmail.org/git?p=notmuch;a=blobdiff_plain;f=lib%2Fregexp-fields.cc;h=0feb50e586ba84f1c4ef84cb62e78ea679b472c3;hp=1651677cd8638b759a9f96838237a98aa2ef5af2;hb=HEAD;hpb=a34f30888e7874fba2032a066a7babce1dd3f69f

diff --git a/lib/regexp-fields.cc b/lib/regexp-fields.cc
index 1651677c..3a775261 100644
--- a/lib/regexp-fields.cc
+++ b/lib/regexp-fields.cc
@@ -25,29 +25,34 @@
 #include "regexp-fields.h"
 #include "notmuch-private.h"
 #include "database-private.h"
+#include "xapian-extra.h"
 
-#if HAVE_XAPIAN_FIELD_PROCESSOR
-static void
-compile_regex (regex_t &regexp, const char *str)
+notmuch_status_t
+compile_regex (regex_t &regexp, const char *str, std::string &msg)
 {
     int err = regcomp (&regexp, str, REG_EXTENDED | REG_NOSUB);
 
     if (err != 0) {
 	size_t len = regerror (err, &regexp, NULL, 0);
 	char *buffer = new char[len];
-	std::string msg;
+	msg = "Regexp error: ";
 	(void) regerror (err, &regexp, buffer, len);
-	msg.assign (buffer, len);
+	msg.append (buffer, len);
 	delete[] buffer;
 
-	throw Xapian::QueryParserError (msg);
+	return NOTMUCH_STATUS_ILLEGAL_ARGUMENT;
     }
+    return NOTMUCH_STATUS_SUCCESS;
 }
 
 RegexpPostingSource::RegexpPostingSource (Xapian::valueno slot, const std::string &regexp)
     : slot_ (slot)
 {
-    compile_regex (regexp_, regexp.c_str ());
+    std::string msg;
+    notmuch_status_t status = compile_regex (regexp_, regexp.c_str (), msg);
+
+    if (status)
+	throw Xapian::QueryParserError (msg);
 }
 
 RegexpPostingSource::~RegexpPostingSource ()
@@ -124,53 +129,124 @@ bool
 RegexpPostingSource::check (Xapian::docid did, unused (double min_wt))
 {
     started_ = true;
-    if (!it_.check (did) || at_end ())
+    if (! it_.check (did) || at_end ())
 	return false;
     return (regexec (&regexp_, (*it_).c_str (), 0, NULL, 0) == 0);
 }
 
-static inline Xapian::valueno _find_slot (std::string prefix)
+static inline Xapian::valueno
+_find_slot (std::string prefix)
 {
     if (prefix == "from")
 	return NOTMUCH_VALUE_FROM;
     else if (prefix == "subject")
 	return NOTMUCH_VALUE_SUBJECT;
+    else if (prefix == "mid")
+	return NOTMUCH_VALUE_MESSAGE_ID;
     else
-	throw Xapian::QueryParserError ("unsupported regexp field '" + prefix + "'");
+	return Xapian::BAD_VALUENO;
 }
 
-RegexpFieldProcessor::RegexpFieldProcessor (std::string prefix, Xapian::QueryParser &parser_, notmuch_database_t *notmuch_)
-	: slot (_find_slot (prefix)), term_prefix (_find_prefix (prefix.c_str ())),
-	  parser (parser_), notmuch (notmuch_)
+RegexpFieldProcessor::RegexpFieldProcessor (std::string field_,
+					    notmuch_field_flag_t options_,
+					    Xapian::QueryParser &parser_,
+					    notmuch_database_t *notmuch_)
+    : slot (_find_slot (field_)),
+    field (field_),
+    term_prefix (_find_prefix (field_.c_str ())),
+    options (options_),
+    parser (parser_),
+    notmuch (notmuch_)
 {
 };
 
+notmuch_status_t
+_notmuch_regexp_to_query (notmuch_database_t *notmuch, Xapian::valueno slot, std::string field,
+			  std::string regexp_str,
+			  Xapian::Query &output, std::string &msg)
+{
+    regex_t regexp;
+    notmuch_status_t status;
+
+    status = compile_regex (regexp, regexp_str.c_str (), msg);
+    if (status) {
+	_notmuch_database_log_append (notmuch, "error compiling regex %s", msg.c_str ());
+	return status;
+    }
+
+    if (slot == Xapian::BAD_VALUENO)
+	slot = _find_slot (field);
+
+    if (slot == Xapian::BAD_VALUENO) {
+	std::string term_prefix = _find_prefix (field.c_str ());
+	std::vector<std::string> terms;
+
+	for (Xapian::TermIterator it = notmuch->xapian_db->allterms_begin (term_prefix);
+	     it != notmuch->xapian_db->allterms_end (); ++it) {
+	    if (regexec (&regexp, (*it).c_str () + term_prefix.size (),
+			 0, NULL, 0) == 0)
+		terms.push_back (*it);
+	}
+	output = Xapian::Query (Xapian::Query::OP_OR, terms.begin (), terms.end ());
+    } else {
+	RegexpPostingSource *postings = new RegexpPostingSource (slot, regexp_str);
+	output = Xapian::Query (postings->release ());
+    }
+    return NOTMUCH_STATUS_SUCCESS;
+}
+
 Xapian::Query
 RegexpFieldProcessor::operator() (const std::string & str)
 {
-    if (str.size () == 0)
-	return Xapian::Query(Xapian::Query::OP_AND_NOT,
-			     Xapian::Query::MatchAll,
-			     Xapian::Query (Xapian::Query::OP_WILDCARD, term_prefix));
+    if (str.empty ()) {
+	if (options & NOTMUCH_FIELD_PROBABILISTIC) {
+	    return Xapian::Query (Xapian::Query::OP_AND_NOT,
+				  xapian_query_match_all (),
+				  Xapian::Query (Xapian::Query::OP_WILDCARD, term_prefix));
+	} else {
+	    return Xapian::Query (term_prefix);
+	}
+    }
 
     if (str.at (0) == '/') {
-	if (str.at (str.size () - 1) == '/'){
-	    RegexpPostingSource *postings = new RegexpPostingSource (slot, str.substr(1,str.size () - 2));
-	    return Xapian::Query (postings->release ());
+	if (str.length () > 1 && str.at (str.size () - 1) == '/') {
+	    Xapian::Query query;
+	    std::string regexp_str = str.substr (1, str.size () - 2);
+	    std::string msg;
+	    notmuch_status_t status;
+
+	    status = _notmuch_regexp_to_query (notmuch, slot, field, regexp_str, query, msg);
+	    if (status)
+		throw Xapian::QueryParserError (msg);
+	    return query;
 	} else {
 	    throw Xapian::QueryParserError ("unmatched regex delimiter in '" + str + "'");
 	}
     } else {
-	/* TODO replace this with a nicer API level triggering of
-	 * phrase parsing, when possible */
-	std::string query_str;
+	if (options & NOTMUCH_FIELD_PROBABILISTIC) {
+	    /* TODO replace this with a nicer API level triggering of
+	     * phrase parsing, when possible */
+	    std::string query_str;
+
+	    if ((str.at (0) != '(' || *str.rbegin () != ')') &&
+		(*str.rbegin () != '*' || str.find (' ') != std::string::npos))
+		query_str = '"' + str + '"';
+	    else
+		query_str = str;
+
+	    return parser.parse_query (query_str, NOTMUCH_QUERY_PARSER_FLAGS, term_prefix);
+	} else {
+	    /* Boolean prefix */
+	    std::string query_str;
+	    std::string term;
 
-	if (str.find (' ') != std::string::npos)
-	    query_str = '"' + str + '"';
-	else
-	    query_str = str;
+	    if (str.length () > 1 && str.at (str.size () - 1) == '/')
+		query_str = str.substr (0, str.size () - 1);
+	    else
+		query_str = str;
 
-	return parser.parse_query (query_str, NOTMUCH_QUERY_PARSER_FLAGS, term_prefix);
+	    term = term_prefix + query_str;
+	    return Xapian::Query (term);
+	}
     }
 }
-#endif