indents and readability

src/common/textsplit.h

@@ -163,6 +163,9 @@ private:
     // Current span. Might be jf.dockes@wanadoo.f
     std::string        m_span; 
 
+    // Words in span: byte positions of start and end of words in m_span. For example:
+    // 0   4    9
+    // bill@some.com -> (0,4) (5,9) (10,13)
     std::vector <std::pair<int, int> > m_words_in_span;
 
     // Current word: no punctuation at all in there. Byte offset

src/common/unacpp.cpp

@@ -1,4 +1,4 @@
-/* Copyright (C) 2004-2019 J.F.Dockes
+/* Copyright (C) 2004-2021 J.F.Dockes
  *   This program is free software; you can redistribute it and/or modify
  *   it under the terms of the GNU General Public License as published by
  *   the Free Software Foundation; either version 2 of the License, or
@@ -37,16 +37,13 @@ bool unacmaybefold(const string &in, string &out,
 
     switch (what) {
     case UNACOP_UNAC:
-        status = unac_string(encoding, in.c_str(), in.length(), 
+        status = unac_string(encoding, in.c_str(), in.length(), &cout, &out_len);
-                             &cout, &out_len);
         break;
     case UNACOP_UNACFOLD:
-        status = unacfold_string(encoding, in.c_str(), in.length(), 
+        status = unacfold_string(encoding, in.c_str(), in.length(), &cout, &out_len);
-                                 &cout, &out_len);
         break;
     case UNACOP_FOLD:
-        status = fold_string(encoding, in.c_str(), in.length(), 
+        status = fold_string(encoding, in.c_str(), in.length(), &cout, &out_len);
-                             &cout, &out_len);
         break;
     }
 

src/query/plaintorich.cpp

@@ -1,4 +1,4 @@
-/* Copyright (C) 2005 J.F.Dockes
+/* Copyright (C) 2005-2021 J.F.Dockes
  *   This program is free software; you can redistribute it and/or modify
  *   it under the terms of the GNU General Public License as published by
  *   the Free Software Foundation; either version 2 of the License, or
@@ -78,8 +78,7 @@ public:
         string dumb = term;
         if (o_index_stripchars) {
             if (!unacmaybefold(term, dumb, "UTF-8", UNACOP_UNACFOLD)) {
-                LOGINFO("PlainToRich::takeword: unac failed for [" << term <<
+                LOGINFO("PlainToRich::takeword: unac failed for [" << term << "]\n");
-                        "]\n");
                 return true;
             }
         }
@@ -173,30 +172,25 @@ static string activate_urls(const string& in)
 }
 #endif
 
-// Fix result text for display inside the gui text window.
+// Enrich result text for display inside the gui text window.
 //
-// We call overridden functions to output header data, beginnings and ends of
+// We call overridden functions to output header data, beginnings and ends of matches etc.
-// matches etc.
 //
-// If the input is text, we output the result in chunks, arranging not
+// If the input is text, we output the result in chunks, arranging not to cut in the middle of a
-// to cut in the middle of a tag, which would confuse qtextedit. If
+// tag, which would confuse qtextedit. If the input is html, the body is always a single output
-// the input is html, the body is always a single output chunk.
+// chunk.
-bool PlainToRich::plaintorich(const string& in, 
+bool PlainToRich::plaintorich(
-                              list<string>& out, // Output chunk list
+    const string& in, list<string>& out, const HighlightData& hdata, int chunksize)
-                              const HighlightData& hdata,
-                              int chunksize)
 {
     Chrono chron;
     bool ret = true;
     LOGDEB1("plaintorichich: in: [" << in << "]\n");
 
     m_hdata = &hdata;
-    // Compute the positions for the query terms.  We use the text
+    // Compute the positions for the query terms.  We use the text splitter to break the text into
-    // splitter to break the text into words, and compare the words to
+    // words, and compare the words to the search terms,
-    // the search terms,
     TextSplitPTR splitter(hdata);
-    // Note: the splitter returns the term locations in byte, not
+    // Note: the splitter returns the term locations in byte, not character, offsets.
-    // character, offsets.
     splitter.text_to_words(in);
     LOGDEB2("plaintorich: split done " << chron.millis() << " mS\n");
     // Compute the positions for NEAR and PHRASE groups.
@@ -205,7 +199,7 @@ bool PlainToRich::plaintorich(const string& in,
 
     out.clear();
     out.push_back("");
-    list<string>::iterator olit = out.begin();
+    auto olit = out.begin();
 
     // Rich text output
     *olit = header();
@@ -225,9 +219,10 @@ bool PlainToRich::plaintorich(const string& in,
     vector<GroupMatchEntry>::iterator tPosEnd = splitter.m_tboffs.end();
 
 #if 0
-    for (vector<pair<int, int> >::const_iterator it = splitter.m_tboffs.begin();
+    for (const auto& region : splitter.m_tboffs) {
-         it != splitter.m_tboffs.end(); it++) {
+        auto st = region.offs.first;
-        LOGDEB2("plaintorich: region: " << it->first << " "<<it->second<< "\n");
+        auto nd = region.offs.second;
+        LOGDEB0("plaintorich: region: " << st << " " << nd << "\n");
     }
 #endif
 
@@ -276,8 +271,7 @@ bool PlainToRich::plaintorich(const string& in,
                 }
                 // Skip all highlight areas that would overlap this one
                 int crend = tPosIt->offs.second;
-                while (tPosIt != splitter.m_tboffs.end() && 
+                while (tPosIt != splitter.m_tboffs.end() && tPosIt->offs.first < crend)
-                       tPosIt->offs.first < crend)
                     tPosIt++;
                 inrcltag = 0;
             }

src/unac/unac.c

@@ -14290,23 +14290,17 @@ int unacmaybefold_string_utf16(const char* in, size_t in_length,
 
     return 0;
 }
-int unac_string_utf16(const char* in, size_t in_length,
+int unac_string_utf16(const char* in, size_t in_length, char** outp, size_t* out_lengthp)
-              char** outp, size_t* out_lengthp)
 {
-    return unacmaybefold_string_utf16(in, in_length,
+    return unacmaybefold_string_utf16(in, in_length, outp, out_lengthp, UNAC_UNAC);
-                      outp, out_lengthp, UNAC_UNAC);
 }
-int unacfold_string_utf16(const char* in, size_t in_length,
+int unacfold_string_utf16(const char* in, size_t in_length, char** outp, size_t* out_lengthp)
-              char** outp, size_t* out_lengthp)
 {
-    return unacmaybefold_string_utf16(in, in_length,
+    return unacmaybefold_string_utf16(in, in_length, outp, out_lengthp, UNAC_UNACFOLD);
-                      outp, out_lengthp, UNAC_UNACFOLD);
 }
-int fold_string_utf16(const char* in, size_t in_length,
+int fold_string_utf16(const char* in, size_t in_length, char** outp, size_t* out_lengthp)
-              char** outp, size_t* out_lengthp)
 {
-    return unacmaybefold_string_utf16(in, in_length,
+    return unacmaybefold_string_utf16(in, in_length, outp, out_lengthp, UNAC_FOLD);
-                      outp, out_lengthp, UNAC_FOLD);
 }
 
 static const char *utf16be = "UTF-16BE";
@@ -14418,10 +14412,11 @@ static int convert(const char* from, const char* to,
                  * should be submited to Unicode so that they can fix the problem.
                  * 
                  */
-    if(from_utf16) {
+                if (from_utf16) {
                     const char* tmp = space;
                     size_t tmp_length = 2;
-      if(iconv(cd, (ICONV_CONST char **) &tmp, &tmp_length, &out, &out_remain) == (size_t)-1) {
+                    if (iconv(cd, (ICONV_CONST char **)&tmp, &tmp_length, &out, &out_remain) ==
+                        (size_t)-1) {
                         if(errno == E2BIG) {
                             /* fall thru to the E2BIG case below */;
                         } else {
@@ -14481,8 +14476,7 @@ out:
     return ret;
 }
 
-int unacmaybefold_string(const char* charset,
+int unacmaybefold_string(const char* charset, const char* in, size_t in_length,
-             const char* in, size_t in_length,
                          char** outp, size_t* out_lengthp, int what)
 {
     /*
@@ -14520,26 +14514,20 @@ int unacmaybefold_string(const char* charset,
     return 0;
 }
 
-int unac_string(const char* charset,
+int unac_string(
-        const char* in, size_t in_length,
+    const char* charset, const char* in, size_t in_length, char** outp, size_t* out_lengthp)
-        char** outp, size_t* out_lengthp)
 {
-    return unacmaybefold_string(charset, in, in_length,
+    return unacmaybefold_string(charset, in, in_length, outp, out_lengthp, UNAC_UNAC);
-                outp, out_lengthp, UNAC_UNAC);
 }
-int unacfold_string(const char* charset,
+int unacfold_string(
-            const char* in, size_t in_length,
+    const char* charset, const char* in, size_t in_length, char** outp, size_t* out_lengthp)
-            char** outp, size_t* out_lengthp)
 {
-    return unacmaybefold_string(charset, in, in_length,
+    return unacmaybefold_string(charset, in, in_length, outp, out_lengthp, UNAC_UNACFOLD);
-                outp, out_lengthp, UNAC_UNACFOLD);
 }
-int fold_string(const char* charset,
+int fold_string(
-            const char* in, size_t in_length,
+    const char* charset, const char* in, size_t in_length, char** outp, size_t* out_lengthp)
-            char** outp, size_t* out_lengthp)
 {
-    return unacmaybefold_string(charset, in, in_length,
+    return unacmaybefold_string(charset, in, in_length, outp, out_lengthp, UNAC_FOLD);
-                outp, out_lengthp, UNAC_FOLD);
 }
 
 const char* unac_version(void)
@@ -14577,15 +14565,13 @@ void unac_set_except_translations(const char *spectrans)
     vector<string> vtrans;
     stringToStrings(spectrans, vtrans);
 
-    for (vector<string>::iterator it = vtrans.begin();
+    for (const auto& trans : vtrans) {
-     it != vtrans.end(); it++) {
 
         /* Convert the whole thing to utf-16be/le according to endianness */
         char *out = 0;
         size_t outsize;
-    if (convert("UTF-8", machinecoding,
+        if (convert("UTF-8", machinecoding, trans.c_str(), trans.size(), &out, &outsize) != 0 ||
-            it->c_str(), it->size(),
+            outsize < 2)
-            &out, &outsize) != 0 || outsize < 2)
             continue;
 
         /* The source char must be utf-16be as this is what we convert the

unac/unac.c

@@ -13,7 +13,7 @@
  *
  * You should have received a copy of the GNU General Public License
  * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
  */
 
 #ifdef BUILDING_RECOLL
@@ -14290,23 +14290,17 @@ int unacmaybefold_string_utf16(const char* in, size_t in_length,
 
     return 0;
 }
-int unac_string_utf16(const char* in, size_t in_length,
+int unac_string_utf16(const char* in, size_t in_length, char** outp, size_t* out_lengthp)
-              char** outp, size_t* out_lengthp)
 {
-    return unacmaybefold_string_utf16(in, in_length,
+    return unacmaybefold_string_utf16(in, in_length, outp, out_lengthp, UNAC_UNAC);
-                      outp, out_lengthp, UNAC_UNAC);
 }
-int unacfold_string_utf16(const char* in, size_t in_length,
+int unacfold_string_utf16(const char* in, size_t in_length, char** outp, size_t* out_lengthp)
-              char** outp, size_t* out_lengthp)
 {
-    return unacmaybefold_string_utf16(in, in_length,
+    return unacmaybefold_string_utf16(in, in_length, outp, out_lengthp, UNAC_UNACFOLD);
-                      outp, out_lengthp, UNAC_UNACFOLD);
 }
-int fold_string_utf16(const char* in, size_t in_length,
+int fold_string_utf16(const char* in, size_t in_length, char** outp, size_t* out_lengthp)
-              char** outp, size_t* out_lengthp)
 {
-    return unacmaybefold_string_utf16(in, in_length,
+    return unacmaybefold_string_utf16(in, in_length, outp, out_lengthp, UNAC_FOLD);
-                      outp, out_lengthp, UNAC_FOLD);
 }
 
 static const char *utf16be = "UTF-16BE";
@@ -14418,10 +14412,11 @@ static int convert(const char* from, const char* to,
                  * should be submited to Unicode so that they can fix the problem.
                  * 
                  */
-    if(from_utf16) {
+                if (from_utf16) {
                     const char* tmp = space;
                     size_t tmp_length = 2;
-      if(iconv(cd, (ICONV_CONST char **) &tmp, &tmp_length, &out, &out_remain) == (size_t)-1) {
+                    if (iconv(cd, (ICONV_CONST char **)&tmp, &tmp_length, &out, &out_remain) ==
+                        (size_t)-1) {
                         if(errno == E2BIG) {
                             /* fall thru to the E2BIG case below */;
                         } else {
@@ -14481,8 +14476,7 @@ out:
     return ret;
 }
 
-int unacmaybefold_string(const char* charset,
+int unacmaybefold_string(const char* charset, const char* in, size_t in_length,
-             const char* in, size_t in_length,
                          char** outp, size_t* out_lengthp, int what)
 {
     /*
@@ -14520,26 +14514,20 @@ int unacmaybefold_string(const char* charset,
     return 0;
 }
 
-int unac_string(const char* charset,
+int unac_string(
-        const char* in, size_t in_length,
+    const char* charset, const char* in, size_t in_length, char** outp, size_t* out_lengthp)
-        char** outp, size_t* out_lengthp)
 {
-    return unacmaybefold_string(charset, in, in_length,
+    return unacmaybefold_string(charset, in, in_length, outp, out_lengthp, UNAC_UNAC);
-                outp, out_lengthp, UNAC_UNAC);
 }
-int unacfold_string(const char* charset,
+int unacfold_string(
-            const char* in, size_t in_length,
+    const char* charset, const char* in, size_t in_length, char** outp, size_t* out_lengthp)
-            char** outp, size_t* out_lengthp)
 {
-    return unacmaybefold_string(charset, in, in_length,
+    return unacmaybefold_string(charset, in, in_length, outp, out_lengthp, UNAC_UNACFOLD);
-                outp, out_lengthp, UNAC_UNACFOLD);
 }
-int fold_string(const char* charset,
+int fold_string(
-            const char* in, size_t in_length,
+    const char* charset, const char* in, size_t in_length, char** outp, size_t* out_lengthp)
-            char** outp, size_t* out_lengthp)
 {
-    return unacmaybefold_string(charset, in, in_length,
+    return unacmaybefold_string(charset, in, in_length, outp, out_lengthp, UNAC_FOLD);
-                outp, out_lengthp, UNAC_FOLD);
 }
 
 const char* unac_version(void)
@@ -14577,15 +14565,13 @@ void unac_set_except_translations(const char *spectrans)
     vector<string> vtrans;
     stringToStrings(spectrans, vtrans);
 
-    for (vector<string>::iterator it = vtrans.begin();
+    for (const auto& trans : vtrans) {
-     it != vtrans.end(); it++) {
 
         /* Convert the whole thing to utf-16be/le according to endianness */
         char *out = 0;
         size_t outsize;
-    if (convert("UTF-8", machinecoding,
+        if (convert("UTF-8", machinecoding, trans.c_str(), trans.size(), &out, &outsize) != 0 ||
-            it->c_str(), it->size(),
+            outsize < 2)
-            &out, &outsize) != 0 || outsize < 2)
             continue;
 
         /* The source char must be utf-16be as this is what we convert the