X-Git-Url: https://git.cworth.org/git?a=blobdiff_plain;f=lib%2Fparse-sexp.cc;h=9f6e0b77f268c19e63e3cb026a5ace2453dccf0f;hb=afe85e65786df1df9abf261393b4b4e6e2e86009;hp=66dbdb4155b619c8974ac282bdf38f90614fde20;hpb=be7e83de96b706af418fc9f139ded4d50bf342f6;p=notmuch

diff --git a/lib/parse-sexp.cc b/lib/parse-sexp.cc
index 66dbdb41..9f6e0b77 100644
--- a/lib/parse-sexp.cc
+++ b/lib/parse-sexp.cc
@@ -1,25 +1,284 @@
-#include <xapian.h>
-#include "notmuch-private.h"
+#include "database-private.h"
 
 #if HAVE_SFSEXP
 #include "sexp.h"
-
+#include "unicode-util.h"
 
 /* _sexp is used for file scope symbols to avoid clashing with
  * definitions from sexp.h */
 
+typedef enum {
+    SEXP_FLAG_NONE	= 0,
+    SEXP_FLAG_FIELD	= 1 << 0,
+    SEXP_FLAG_BOOLEAN	= 1 << 1,
+    SEXP_FLAG_SINGLE	= 1 << 2,
+    SEXP_FLAG_WILDCARD	= 1 << 3,
+    SEXP_FLAG_REGEX	= 1 << 4,
+    SEXP_FLAG_DO_REGEX	= 1 << 5,
+    SEXP_FLAG_EXPAND	= 1 << 6,
+    SEXP_FLAG_DO_EXPAND = 1 << 7,
+} _sexp_flag_t;
+
+/*
+ * define bitwise operators to hide casts */
+
+inline _sexp_flag_t
+operator| (_sexp_flag_t a, _sexp_flag_t b)
+{
+    return static_cast<_sexp_flag_t>(
+	static_cast<unsigned>(a) | static_cast<unsigned>(b));
+}
+
+inline _sexp_flag_t
+operator& (_sexp_flag_t a, _sexp_flag_t b)
+{
+    return static_cast<_sexp_flag_t>(
+	static_cast<unsigned>(a) & static_cast<unsigned>(b));
+}
+
+typedef struct  {
+    const char *name;
+    Xapian::Query::op xapian_op;
+    Xapian::Query initial;
+    _sexp_flag_t flags;
+} _sexp_prefix_t;
+
+static _sexp_prefix_t prefixes[] =
+{
+    { "and",            Xapian::Query::OP_AND,          Xapian::Query::MatchAll,
+      SEXP_FLAG_NONE },
+    { "attachment",     Xapian::Query::OP_AND,          Xapian::Query::MatchAll,
+      SEXP_FLAG_FIELD | SEXP_FLAG_WILDCARD | SEXP_FLAG_EXPAND },
+    { "body",           Xapian::Query::OP_AND,          Xapian::Query::MatchAll,
+      SEXP_FLAG_FIELD },
+    { "from",           Xapian::Query::OP_AND,          Xapian::Query::MatchAll,
+      SEXP_FLAG_FIELD | SEXP_FLAG_WILDCARD | SEXP_FLAG_REGEX | SEXP_FLAG_EXPAND },
+    { "folder",         Xapian::Query::OP_OR,           Xapian::Query::MatchNothing,
+      SEXP_FLAG_FIELD | SEXP_FLAG_BOOLEAN | SEXP_FLAG_WILDCARD | SEXP_FLAG_REGEX | SEXP_FLAG_EXPAND },
+    { "id",             Xapian::Query::OP_OR,           Xapian::Query::MatchNothing,
+      SEXP_FLAG_FIELD | SEXP_FLAG_BOOLEAN | SEXP_FLAG_WILDCARD | SEXP_FLAG_REGEX },
+    { "is",             Xapian::Query::OP_AND,          Xapian::Query::MatchAll,
+      SEXP_FLAG_FIELD | SEXP_FLAG_BOOLEAN | SEXP_FLAG_WILDCARD | SEXP_FLAG_REGEX | SEXP_FLAG_EXPAND },
+    { "matching",       Xapian::Query::OP_AND,          Xapian::Query::MatchAll,
+      SEXP_FLAG_DO_EXPAND },
+    { "mid",            Xapian::Query::OP_OR,           Xapian::Query::MatchNothing,
+      SEXP_FLAG_FIELD | SEXP_FLAG_BOOLEAN | SEXP_FLAG_WILDCARD | SEXP_FLAG_REGEX },
+    { "mimetype",       Xapian::Query::OP_AND,          Xapian::Query::MatchAll,
+      SEXP_FLAG_FIELD | SEXP_FLAG_WILDCARD | SEXP_FLAG_EXPAND },
+    { "not",            Xapian::Query::OP_AND_NOT,      Xapian::Query::MatchAll,
+      SEXP_FLAG_NONE },
+    { "of",             Xapian::Query::OP_AND,          Xapian::Query::MatchAll,
+      SEXP_FLAG_DO_EXPAND },
+    { "or",             Xapian::Query::OP_OR,           Xapian::Query::MatchNothing,
+      SEXP_FLAG_NONE },
+    { "path",           Xapian::Query::OP_OR,           Xapian::Query::MatchNothing,
+      SEXP_FLAG_FIELD | SEXP_FLAG_BOOLEAN | SEXP_FLAG_WILDCARD | SEXP_FLAG_REGEX },
+    { "property",       Xapian::Query::OP_AND,          Xapian::Query::MatchAll,
+      SEXP_FLAG_FIELD | SEXP_FLAG_BOOLEAN | SEXP_FLAG_WILDCARD | SEXP_FLAG_REGEX | SEXP_FLAG_EXPAND },
+    { "regex",          Xapian::Query::OP_INVALID,      Xapian::Query::MatchAll,
+      SEXP_FLAG_SINGLE | SEXP_FLAG_DO_REGEX },
+    { "rx",             Xapian::Query::OP_INVALID,      Xapian::Query::MatchAll,
+      SEXP_FLAG_SINGLE | SEXP_FLAG_DO_REGEX },
+    { "starts-with",    Xapian::Query::OP_WILDCARD,     Xapian::Query::MatchAll,
+      SEXP_FLAG_SINGLE },
+    { "subject",        Xapian::Query::OP_AND,          Xapian::Query::MatchAll,
+      SEXP_FLAG_FIELD | SEXP_FLAG_WILDCARD | SEXP_FLAG_REGEX | SEXP_FLAG_EXPAND },
+    { "tag",            Xapian::Query::OP_AND,          Xapian::Query::MatchAll,
+      SEXP_FLAG_FIELD | SEXP_FLAG_BOOLEAN | SEXP_FLAG_WILDCARD | SEXP_FLAG_REGEX | SEXP_FLAG_EXPAND },
+    { "thread",         Xapian::Query::OP_OR,           Xapian::Query::MatchNothing,
+      SEXP_FLAG_FIELD | SEXP_FLAG_BOOLEAN | SEXP_FLAG_WILDCARD | SEXP_FLAG_REGEX | SEXP_FLAG_EXPAND },
+    { "to",             Xapian::Query::OP_AND,          Xapian::Query::MatchAll,
+      SEXP_FLAG_FIELD | SEXP_FLAG_WILDCARD | SEXP_FLAG_EXPAND },
+    { }
+};
+
+static notmuch_status_t _sexp_to_xapian_query (notmuch_database_t *notmuch,
+					       const _sexp_prefix_t *parent,
+					       const sexp_t *sx,
+					       Xapian::Query &output);
+
+static notmuch_status_t
+_sexp_combine_query (notmuch_database_t *notmuch,
+		     const _sexp_prefix_t *parent,
+		     Xapian::Query::op operation,
+		     Xapian::Query left,
+		     const sexp_t *sx,
+		     Xapian::Query &output)
+{
+    Xapian::Query subquery;
+
+    notmuch_status_t status;
+
+    /* if we run out elements, return accumulator */
+
+    if (! sx) {
+	output = left;
+	return NOTMUCH_STATUS_SUCCESS;
+    }
+
+    status = _sexp_to_xapian_query (notmuch, parent, sx, subquery);
+    if (status)
+	return status;
+
+    return _sexp_combine_query (notmuch,
+				parent,
+				operation,
+				Xapian::Query (operation, left, subquery),
+				sx->next, output);
+}
+
+static notmuch_status_t
+_sexp_parse_phrase (std::string term_prefix, const char *phrase, Xapian::Query &output)
+{
+    Xapian::Utf8Iterator p (phrase);
+    Xapian::Utf8Iterator end;
+    std::vector<std::string> terms;
+
+    while (p != end) {
+	Xapian::Utf8Iterator start;
+	while (p != end && ! Xapian::Unicode::is_wordchar (*p))
+	    p++;
+
+	if (p == end)
+	    break;
+
+	start = p;
+
+	while (p != end && Xapian::Unicode::is_wordchar (*p))
+	    p++;
+
+	if (p != start) {
+	    std::string word (start, p);
+	    word = Xapian::Unicode::tolower (word);
+	    terms.push_back (term_prefix + word);
+	}
+    }
+    output = Xapian::Query (Xapian::Query::OP_PHRASE, terms.begin (), terms.end ());
+    return NOTMUCH_STATUS_SUCCESS;
+}
+
+static notmuch_status_t
+_sexp_parse_wildcard (notmuch_database_t *notmuch,
+		      const _sexp_prefix_t *parent,
+		      std::string match,
+		      Xapian::Query &output)
+{
+
+    std::string term_prefix = parent ? _find_prefix (parent->name) : "";
+
+    if (parent && ! (parent->flags & SEXP_FLAG_WILDCARD)) {
+	_notmuch_database_log (notmuch, "'%s' does not support wildcard queries\n", parent->name);
+	return NOTMUCH_STATUS_BAD_QUERY_SYNTAX;
+    }
+
+    output = Xapian::Query (Xapian::Query::OP_WILDCARD,
+			    term_prefix + Xapian::Unicode::tolower (match));
+    return NOTMUCH_STATUS_SUCCESS;
+}
+
+static notmuch_status_t
+_sexp_parse_one_term (notmuch_database_t *notmuch, std::string term_prefix, const sexp_t *sx,
+		      Xapian::Query &output)
+{
+    Xapian::Stem stem = *(notmuch->stemmer);
+
+    if (sx->aty == SEXP_BASIC && unicode_word_utf8 (sx->val)) {
+	std::string term = Xapian::Unicode::tolower (sx->val);
+
+	output = Xapian::Query ("Z" + term_prefix + stem (term));
+	return NOTMUCH_STATUS_SUCCESS;
+    } else {
+	return _sexp_parse_phrase (term_prefix, sx->val, output);
+    }
+
+}
+
+notmuch_status_t
+_sexp_parse_regex (notmuch_database_t *notmuch,
+		   const _sexp_prefix_t *prefix, const _sexp_prefix_t *parent,
+		   std::string val, Xapian::Query &output)
+{
+    if (! parent) {
+	_notmuch_database_log (notmuch, "illegal '%s' outside field\n",
+			       prefix->name);
+	return NOTMUCH_STATUS_BAD_QUERY_SYNTAX;
+    }
+
+    if (! (parent->flags & SEXP_FLAG_REGEX)) {
+	_notmuch_database_log (notmuch, "'%s' not supported in field '%s'\n",
+			       prefix->name, parent->name);
+	return NOTMUCH_STATUS_BAD_QUERY_SYNTAX;
+    }
+
+    std::string msg; /* ignored */
+
+    return _notmuch_regexp_to_query (notmuch, Xapian::BAD_VALUENO, parent->name,
+				     val, output, msg);
+}
+
+
+static notmuch_status_t
+_sexp_expand_query (notmuch_database_t *notmuch,
+		    const _sexp_prefix_t *prefix, const _sexp_prefix_t *parent,
+		    const sexp_t *sx, Xapian::Query &output)
+{
+    Xapian::Query subquery;
+    notmuch_status_t status;
+    std::string msg;
+
+    if (! (parent->flags & SEXP_FLAG_EXPAND)) {
+	_notmuch_database_log (notmuch, "'%s' unsupported inside '%s'\n", prefix->name, parent->name);
+	return NOTMUCH_STATUS_BAD_QUERY_SYNTAX;
+    }
+
+    status = _sexp_combine_query (notmuch, NULL, prefix->xapian_op, prefix->initial, sx, subquery);
+    if (status)
+	return status;
+
+    status = _notmuch_query_expand (notmuch, parent->name, subquery, output, msg);
+    if (status) {
+	_notmuch_database_log (notmuch, "error expanding query %s\n", msg.c_str ());
+    }
+    return status;
+}
+
 /* Here we expect the s-expression to be a proper list, with first
  * element defining and operation, or as a special case the empty
  * list */
 
 static notmuch_status_t
-_sexp_to_xapian_query (notmuch_database_t *notmuch, const sexp_t *sx,
+_sexp_to_xapian_query (notmuch_database_t *notmuch, const _sexp_prefix_t *parent, const sexp_t *sx,
 		       Xapian::Query &output)
 {
-
     if (sx->ty == SEXP_VALUE) {
-	output = Xapian::Query (Xapian::Unicode::tolower (sx->val));
-	return NOTMUCH_STATUS_SUCCESS;
+	std::string term_prefix = parent ? _find_prefix (parent->name) : "";
+
+	if (sx->aty == SEXP_BASIC && strcmp (sx->val, "*") == 0) {
+	    return _sexp_parse_wildcard (notmuch, parent, "", output);
+	}
+
+	if (parent && (parent->flags & SEXP_FLAG_BOOLEAN)) {
+	    output = Xapian::Query (term_prefix + sx->val);
+	    return NOTMUCH_STATUS_SUCCESS;
+	}
+	if (parent) {
+	    return _sexp_parse_one_term (notmuch, term_prefix, sx, output);
+	} else {
+	    Xapian::Query accumulator;
+	    for (_sexp_prefix_t *prefix = prefixes; prefix->name; prefix++) {
+		if (prefix->flags & SEXP_FLAG_FIELD) {
+		    notmuch_status_t status;
+		    Xapian::Query subquery;
+		    term_prefix = _find_prefix (prefix->name);
+		    status = _sexp_parse_one_term (notmuch, term_prefix, sx, subquery);
+		    if (status)
+			return status;
+		    accumulator = Xapian::Query (Xapian::Query::OP_OR, accumulator, subquery);
+		}
+	    }
+	    output = accumulator;
+	    return NOTMUCH_STATUS_SUCCESS;
+	}
     }
 
     /* Empty list */
@@ -28,11 +287,47 @@ _sexp_to_xapian_query (notmuch_database_t *notmuch, const sexp_t *sx,
 	return NOTMUCH_STATUS_SUCCESS;
     }
 
-    if (sx->list->ty == SEXP_VALUE)
-	_notmuch_database_log (notmuch, "unknown prefix '%s'\n", sx->list->val);
-    else
+    if (sx->list->ty == SEXP_LIST) {
 	_notmuch_database_log (notmuch, "unexpected list in field/operation position\n",
 			       sx->list->val);
+	return NOTMUCH_STATUS_BAD_QUERY_SYNTAX;
+    }
+
+    for (_sexp_prefix_t *prefix = prefixes; prefix && prefix->name; prefix++) {
+	if (strcmp (prefix->name, sx->list->val) == 0) {
+	    if (prefix->flags & SEXP_FLAG_FIELD) {
+		if (parent) {
+		    _notmuch_database_log (notmuch, "nested field: '%s' inside '%s'\n",
+					   prefix->name, parent->name);
+		    return NOTMUCH_STATUS_BAD_QUERY_SYNTAX;
+		}
+		parent = prefix;
+	    }
+
+	    if ((prefix->flags & SEXP_FLAG_SINGLE) &&
+		(! sx->list->next || sx->list->next->next || sx->list->next->ty != SEXP_VALUE)) {
+		_notmuch_database_log (notmuch, "'%s' expects single atom as argument\n",
+				       prefix->name);
+		return NOTMUCH_STATUS_BAD_QUERY_SYNTAX;
+	    }
+
+	    if (prefix->xapian_op == Xapian::Query::OP_WILDCARD)
+		return _sexp_parse_wildcard (notmuch, parent, sx->list->next->val, output);
+
+	    if (prefix->flags & SEXP_FLAG_DO_REGEX) {
+		return _sexp_parse_regex (notmuch, prefix, parent, sx->list->next->val, output);
+	    }
+
+	    if (prefix->flags & SEXP_FLAG_DO_EXPAND) {
+		return _sexp_expand_query (notmuch, prefix, parent, sx->list->next, output);
+	    }
+
+	    return _sexp_combine_query (notmuch, parent, prefix->xapian_op, prefix->initial,
+					sx->list->next, output);
+	}
+    }
+
+    _notmuch_database_log (notmuch, "unknown prefix '%s'\n", sx->list->val);
 
     return NOTMUCH_STATUS_BAD_QUERY_SYNTAX;
 }
@@ -50,6 +345,6 @@ _notmuch_sexp_string_to_xapian_query (notmuch_database_t *notmuch, const char *q
 	return NOTMUCH_STATUS_BAD_QUERY_SYNTAX;
     }
 
-    return _sexp_to_xapian_query (notmuch, sx, output);
+    return _sexp_to_xapian_query (notmuch, NULL, sx, output);
 }
 #endif