add underscoreasletter config variable to process _ as a letter

src/common/textsplit.cpp

@@ -118,6 +118,13 @@ void TextSplit::staticConfInit(RclConfig *config)
         }
     }
 
+    bvalue = false;
+    if (config->getConfParam("underscoreasletter", &bvalue)) {
+        if (bvalue) {
+            charclasses[int('_')] = A_LLETTER;
+        }
+    }
+
     string kotagger;
     config->getConfParam("hangultagger", kotagger);
     if (!kotagger.empty()) {
@@ -855,7 +862,7 @@ 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.