Merge branch 'master' of https://framagit.org/medoc91/recoll

packaging/debian/buildppa.sh

@@ -6,7 +6,7 @@
 
 PPA_KEYID=7808CE96D38B9201
 
-RCLVERS=1.27.5
+RCLVERS=1.27.6
 SCOPEVERS=1.20.2.4
 GSSPVERS=1.0.0
 PPAVERS=1
@@ -49,7 +49,7 @@ debdir=debian
 # 16.04LTS xenial 2021-04
 # 18.04LTS bionic 2023-04
 # 20.04LTS focal  2025-04
-series="xenial bionic focal"
+series="xenial bionic focal groovy"
 series=
 
 if test "X$series" != X ; then
@@ -89,8 +89,8 @@ done
 # 16.04LTS xenial 2021-04
 # 18.04LTS bionic 2023-04
 # 20.04LTS focal  2025-04
-series="xenial bionic focal"
+series="xenial bionic focal groovy"
-#series=
+# series=
 
 debdir=debiankio
 topdir=kio-recoll-${RCLVERS}
@@ -133,7 +133,7 @@ done
 # 16.04LTS xenial 2021-04
 # 18.04LTS bionic 2023-04
 # 20.04LTS focal  2025-04
-series="xenial bionic focal"
+series="xenial bionic focal groovy"
 series=
 
 debdir=debiangssp

packaging/debian/debian/changelog

@@ -1,3 +1,15 @@
+recoll (1.27.6-1~ppaPPAVERS~SERIES1) SERIES; urgency=low
+
+  * Process PDF annotations if the poppler-glib Python bindings are available
+  * Fix build error with some compiler versions
+  * Fix inconsistent lock file name issue which could result in background
+    indexer exit.
+  * recollq: new -p option to show snippets lists instead of abstracts with
+    -A
+  * Fix nonumbers option.
+
+ -- Jean-Francois Dockes <jf@dockes.org>  Sun, 13 Sep 2020 13:29:00 +0200
+
 recoll (1.27.5-1~ppaPPAVERS~SERIES1) SERIES; urgency=low
 
   * Misc small fixes.

packaging/debian/debiankio/changelog

@@ -1,3 +1,15 @@
+kio-recoll (1.27.6-1~ppaPPAVERS~SERIES1) SERIES; urgency=low
+
+  * Process PDF annotations if the poppler-glib Python bindings are available
+  * Fix build error with some compiler versions
+  * Fix inconsistent lock file name issue which could result in background
+    indexer exit.
+  * recollq: new -p option to show snippets lists instead of abstracts with
+    -A
+  * Fix nonumbers option.
+
+ -- Jean-Francois Dockes <jf@dockes.org>  Sun, 13 Sep 2020 13:29:00 +0200
+
 kio-recoll (1.27.5-1~ppaPPAVERS~SERIES1) SERIES; urgency=low
 
   * Misc small fixes.

src/VERSION

@@ -1 +1 @@
-1.27.6
+1.27.7

src/common/textsplit.cpp

@@ -84,6 +84,9 @@ int           TextSplit::o_maxWordLength{40};
 static const int o_CJKMaxNgramLen{5};
 bool o_exthangultagger{false};
 
+// This is changed to 0 if _ is processed as a letter
+static char underscoreatend = '_';
+
 void TextSplit::staticConfInit(RclConfig *config)
 {
     config->getConfParam("maxtermlength", &o_maxWordLength);
@@ -118,6 +121,14 @@ void TextSplit::staticConfInit(RclConfig *config)
         }
     }
 
+    bvalue = false;
+    if (config->getConfParam("underscoreasletter", &bvalue)) {
+        if (bvalue) {
+            charclasses[int('_')] = A_LLETTER;
+            underscoreatend = 0;
+        }
+    }
+
     string kotagger;
     config->getConfParam("hangultagger", kotagger);
     if (!kotagger.empty()) {
@@ -550,26 +561,26 @@ inline bool TextSplit::doemit(bool spanerase, size_t _bp)
 
     // Maybe trim at end. These are chars that we might keep
     // inside a span, but not at the end.
-    while (m_span.length() > 0) {
+    string::size_type trimsz{0};
-        switch (*(m_span.rbegin())) {
+    while (trimsz < m_span.length()) {
-        case '.':
+        auto c = m_span[m_span.length() - 1 - trimsz];
-        case '-':
+        if (c == '.' || c == '-' || c == ',' || c == '@' || c == '\'' ||
-        case ',':
+            c == underscoreatend) {
-        case '@':
+            trimsz++;
-        case '_':
-        case '\'':
-            m_span.resize(m_span.length()-1);
             if (m_words_in_span.size() &&
-                m_words_in_span.back().second > int(m_span.size()))
+                m_words_in_span.back().second > int(m_span.size())) {
                 m_words_in_span.back().second = int(m_span.size());
-            if (--bp < 0) 
+            }
+            if (--bp < 0) {
                 bp = 0;
+            }
+        } else {
             break;
-        default:
-            goto breaktrimloop;
         }
     }
-breaktrimloop:
+    if (trimsz > 0) {
+        m_span.resize(m_span.length() - trimsz);
+    }
 
     if (!words_from_span(bp)) {
         return false;
@@ -855,7 +866,7 @@ bool TextSplit::text_to_words(const string &in)
             goto SPACE;
 
         case '@':
-        case '_':
+        case '_': // If underscoreasletter is set, we'll never get this
         case '\'':
             // If in word, potential span: o'brien, jf@dockes.org,
             // else just ignore

src/doc/user/recoll.conf.xml

@@ -253,8 +253,12 @@ in version 1.22, and on by default. Setting the variable to off allows
 restoring the previous behaviour.</para></listitem></varlistentry>
 <varlistentry id="RCL.INSTALL.CONFIG.RECOLLCONF.BACKSLASHASLETTER">
 <term><varname>backslashasletter</varname></term>
-<listitem><para>Process backslash as normal letter This may make sense for people wanting to index TeX commands as
+<listitem><para>Process backslash as normal letter. This may make sense for people wanting to index TeX commands as
 such but is not of much general use.</para></listitem></varlistentry>
+<varlistentry id="RCL.INSTALL.CONFIG.RECOLLCONF.UNDERSCOREASLETTER">
+<term><varname>underscoreasletter</varname></term>
+<listitem><para>Process underscore as normal letter. This makes sense in so many cases that one wonders if it should
+not be the default.</para></listitem></varlistentry>
 <varlistentry id="RCL.INSTALL.CONFIG.RECOLLCONF.MAXTERMLENGTH">
 <term><varname>maxtermlength</varname></term>
 <listitem><para>Maximum term length. Words longer than this will be discarded.
@@ -758,7 +762,7 @@ script. Example values: eng, fra... See the tesseract documentation.</para></lis
 <term><varname>tesseractcmd</varname></term>
 <listitem><para>Path for the tesseract command. This is mostly useful on Windows, or for specifying a non-default
 tesseract command. e.g. on Windows:
-C:/Program&nbsp;Files&nbsp;(x86)/Tesseract-OCR/tesseract.exe</para></listitem></varlistentry>
+C:/ProgramFiles(x86)/Tesseract-OCR/tesseract.exe</para></listitem></varlistentry>
 <varlistentry id="RCL.INSTALL.CONFIG.RECOLLCONF.ABBYYLANG">
 <term><varname>abbyylang</varname></term>
 <listitem><para>Language to assume for abbyy OCR. Important for improving the OCR accuracy. This can also be set

src/doc/user/usermanual.html

@@ -8933,12 +8933,21 @@ for i in range(nres):
                 id=
                 "RCL.INSTALL.CONFIG.RECOLLCONF.BACKSLASHASLETTER"></a><span class="term"><code class="varname">backslashasletter</code></span></dt>
                 <dd>
-                  <p>Process backslash as normal letter This may
+                  <p>Process backslash as normal letter. This may
                   make sense for people wanting to index TeX
                   commands as such but is not of much general
                   use.</p>
                 </dd>
                 <dt><a name=
+                "RCL.INSTALL.CONFIG.RECOLLCONF.UNDERSCOREASLETTER"
+                id=
+                "RCL.INSTALL.CONFIG.RECOLLCONF.UNDERSCOREASLETTER"></a><span class="term"><code class="varname">underscoreasletter</code></span></dt>
+                <dd>
+                  <p>Process underscore as normal letter. This
+                  makes sense in so many cases that one wonders if
+                  it should not be the default.</p>
+                </dd>
+                <dt><a name=
                 "RCL.INSTALL.CONFIG.RECOLLCONF.MAXTERMLENGTH" id=
                 "RCL.INSTALL.CONFIG.RECOLLCONF.MAXTERMLENGTH"></a><span class="term"><code class="varname">maxtermlength</code></span></dt>
                 <dd>
@@ -9865,7 +9874,7 @@ for i in range(nres):
                   <p>Path for the tesseract command. This is mostly
                   useful on Windows, or for specifying a
                   non-default tesseract command. e.g. on Windows:
-                  C:/Program&nbsp;Files&nbsp;(x86)/Tesseract-OCR/tesseract.exe</p>
+                  C:/ProgramFiles(x86)/Tesseract-OCR/tesseract.exe</p>
                 </dd>
                 <dt><a name=
                 "RCL.INSTALL.CONFIG.RECOLLCONF.ABBYYLANG" id=

src/sampleconf/recoll.conf

@@ -317,12 +317,19 @@ indexStoreDocText = 1
 #dehyphenate = 1
 
 # <var name="backslashasletter" type="bool">
-#  <brief>Process backslash as normal letter</brief>
+#  <brief>Process backslash as normal letter.</brief>
 #  <descr>This may make sense for people wanting to index TeX commands as
 #  such but is not of much general use.</descr>
 # </var>
 #backslashasletter = 0
 
+# <var name="underscoreasletter" type="bool">
+#  <brief>Process underscore as normal letter.</brief>
+#  <descr>This makes sense in so many cases that one wonders if it should
+#  not be the default.</descr>
+# </var>
+#underscoreasletter = 0
+
 # <var name="maxtermlength" type="int" values="10 200 40">
 #  <brief>Maximum term length.</brief>
 #  <descr>Words longer than this will be discarded.

src/testmains/trtextsplit.cpp

@@ -265,6 +265,7 @@ int main(int argc, char **argv)
     if (!kotagger.empty()) {
         fprintf(fp, "hangultagger = %s\n", kotagger.c_str());
     }
+    fprintf(fp, "underscoreasletter = 0\n");
     fclose(fp);
 
     Logger::getTheLog("")->setLogLevel(Logger::LogLevel(loglevel));