[prev in list] [next in list] [prev in thread] [next in thread] 

List:       kde-commits
Subject:    playground/base/strigi/src/streamindexer
From:       Jos van den Oever <jos () vandenoever ! info>
Date:       2006-06-30 15:05:03
Message-ID: 1151679903.325269.3860.nullmailer () svn ! kde ! org
[Download RAW message or body]

SVN commit 556530 by vandenoever:

slight refactoring

 M  +1 -1      Makefile.am  
 D             indexreader.cpp  
 M  +100 -0    query.cpp  


--- trunk/playground/base/strigi/src/streamindexer/Makefile.am #556529:556530
@@ -3,7 +3,7 @@
 libstreamindexer_la_SOURCES = bz2endanalyzer.cpp digestthroughanalyzer.cpp \
 	textendanalyzer.cpp streamendanalyzer.cpp zipendanalyzer.cpp \
 	tarendanalyzer.cpp streamindexer.cpp pngendanalyzer.cpp query.cpp\
-	mailendanalyzer.cpp gzipendanalyzer.cpp filelister.cpp indexreader.cpp \
+	mailendanalyzer.cpp gzipendanalyzer.cpp filelister.cpp \
 	mimetypethroughanalyzer.cpp pluginthroughanalyzer.cpp indexwriter.cpp \
 	saxendanalyzer.cpp
 
--- trunk/playground/base/strigi/src/streamindexer/query.cpp #556529:556530
@@ -2,6 +2,106 @@
 using namespace std;
 using namespace jstreams;
 
+/**
+ * The constructor parses the query in include and exclude statements.
+ * The following lines contain example queries.
+ * hi
+ * 'hi'
+ * hi Jos
+ * 'hi Jos'
+ * "hi Jos"
+ * -hi Jos
+ * path:"hi Jos"
+ * -path:"hi Jos"
+ * So the syntax is something like this:
+ * query ::= [term]*
+ * term ::= [-][prefix]:("searchphrase"|searchphrase)
+ **/
+
+Query::Query(const string& query, int max, int offset) {
+    this->max = max;
+    this->offset = offset;
+    const char* q = query.c_str();
+    const char* end = q+query.length();
+    const char* p = q;
+    while (p < end) {
+        p = parseTerm(p);
+    }
+/*    map<string, set<string> >::const_iterator i;
+    set<string>::const_iterator j;
+    for (i = includes.begin(); i != includes.end(); ++i) {
+        for (j = i->second.begin(); j != i->second.end(); ++j) {
+            printf("+ '%s':'%s'\n", i->first.c_str(), j->c_str());
+        }
+    }
+    for (i = excludes.begin(); i != excludes.end(); ++i) {
+        for (j = i->second.begin(); j != i->second.end(); ++j) {
+            printf("- '%s':'%s'\n", i->first.c_str(), j->c_str());
+        }
+    }
+    printf("--\n");*/
+}
+const char*
+Query::parseTerm(const char* s) {
+    bool include = true;
+    const char* p = s;
+    // skip whitespace
+    while (*p != '\0' && isspace(*p)) p++;
+    if (*p == '\0') return p;
+
+    // check for a - sign
+    if (*p == '-') {
+        include = false;
+        p++;
+    }
+    // skip whitespace
+    while (*p != '\0' && isspace(*p)) p++;
+    if (*p == '\0') return p;
+
+    char quote = 0;
+    if (*p == '\'' || *p == '"') {
+        quote = *p++;
+        if (*p == '\0') return p;
+    }
+    const char* prefix = 0;
+    const char* prefend;
+    const char* term = p;
+    // skip until end of string or closing quote or colon or whitespace
+    while (*p != '\0' && ((quote == 0 && !isspace(*p))
+            || (quote != 0 && *p != quote))) {
+        if (quote == 0 && *p == ':') {
+            // define the prefix
+            prefix = term;
+            prefend = p;
+            ++p;
+            if (*p == '\0') return p;
+            if (*p == '\'' || *p == '"') {
+                quote = *p++;
+                if (*p == '\0') return p;
+            }
+            term = p;
+        }
+        ++p;
+    }
+    if (*term == '\0') return term;
+    if (p - term > 0) {
+        string pre;
+        string ter;
+        if (prefix != 0 && term - prefix > 1) {
+            pre = string(prefix, prefend-prefix);
+        }
+        ter = string(term, p-term);
+        if (include) {
+            includes[pre].insert(ter);
+        } else {
+            excludes[pre].insert(ter);
+        }
+    }
+    // skip the terminating character
+    if (p != '\0') p++;
+    return p;
+}
+
 void
 replaceall(string& text, const string& a, const string& b) {
     size_t pos = 0;
[prev in list] [next in list] [prev in thread] [next in thread]