<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN"> <html> <head> <link rel="stylesheet" href="style.css" type="text/css"> <meta content="text/html; charset=iso-8859-1" http-equiv="Content-Type"> <link rel="Start" href="index.html"> <link rel="previous" href="BatGc.html"> <link rel="next" href="BatGlobal.html"> <link rel="Up" href="index.html"> <link title="Index of types" rel=Appendix href="index_types.html"> <link title="Index of exceptions" rel=Appendix href="index_exceptions.html"> <link title="Index of values" rel=Appendix href="index_values.html"> <link title="Index of class methods" rel=Appendix href="index_methods.html"> <link title="Index of classes" rel=Appendix href="index_classes.html"> <link title="Index of modules" rel=Appendix href="index_modules.html"> <link title="Index of module types" rel=Appendix href="index_module_types.html"> <link title="BatArray" rel="Chapter" href="BatArray.html"> <link title="BatAvlTree" rel="Chapter" href="BatAvlTree.html"> <link title="BatBase64" rel="Chapter" href="BatBase64.html"> <link title="BatBig_int" rel="Chapter" href="BatBig_int.html"> <link title="BatBigarray" rel="Chapter" href="BatBigarray.html"> <link title="BatBitSet" rel="Chapter" href="BatBitSet.html"> <link title="BatBool" rel="Chapter" href="BatBool.html"> <link title="BatBounded" rel="Chapter" href="BatBounded.html"> <link title="BatBuffer" rel="Chapter" href="BatBuffer.html"> <link title="BatCache" rel="Chapter" href="BatCache.html"> <link title="BatChar" rel="Chapter" href="BatChar.html"> <link title="BatCharParser" rel="Chapter" href="BatCharParser.html"> <link title="BatComplex" rel="Chapter" href="BatComplex.html"> <link title="BatConcurrent" rel="Chapter" href="BatConcurrent.html"> <link title="BatDeque" rel="Chapter" href="BatDeque.html"> <link title="BatDigest" rel="Chapter" href="BatDigest.html"> <link title="BatDllist" rel="Chapter" href="BatDllist.html"> <link title="BatDynArray" rel="Chapter" href="BatDynArray.html"> <link title="BatEnum" rel="Chapter" href="BatEnum.html"> <link title="BatFile" rel="Chapter" href="BatFile.html"> <link title="BatFingerTree" rel="Chapter" href="BatFingerTree.html"> <link title="BatFloat" rel="Chapter" href="BatFloat.html"> <link title="BatFormat" rel="Chapter" href="BatFormat.html"> <link title="BatGc" rel="Chapter" href="BatGc.html"> <link title="BatGenlex" rel="Chapter" href="BatGenlex.html"> <link title="BatGlobal" rel="Chapter" href="BatGlobal.html"> <link title="BatHashcons" rel="Chapter" href="BatHashcons.html"> <link title="BatHashtbl" rel="Chapter" href="BatHashtbl.html"> <link title="BatHeap" rel="Chapter" href="BatHeap.html"> <link title="BatIMap" rel="Chapter" href="BatIMap.html"> <link title="BatIO" rel="Chapter" href="BatIO.html"> <link title="BatISet" rel="Chapter" href="BatISet.html"> <link title="BatInnerIO" rel="Chapter" href="BatInnerIO.html"> <link title="BatInnerPervasives" rel="Chapter" href="BatInnerPervasives.html"> <link title="BatInnerWeaktbl" rel="Chapter" href="BatInnerWeaktbl.html"> <link title="BatInt" rel="Chapter" href="BatInt.html"> <link title="BatInt32" rel="Chapter" href="BatInt32.html"> <link title="BatInt64" rel="Chapter" href="BatInt64.html"> <link title="BatInterfaces" rel="Chapter" href="BatInterfaces.html"> <link title="BatLazyList" rel="Chapter" href="BatLazyList.html"> <link title="BatLexing" rel="Chapter" href="BatLexing.html"> <link title="BatList" rel="Chapter" href="BatList.html"> <link title="BatLog" rel="Chapter" href="BatLog.html"> <link title="BatLogger" rel="Chapter" href="BatLogger.html"> <link title="BatMap" rel="Chapter" href="BatMap.html"> <link title="BatMarshal" rel="Chapter" href="BatMarshal.html"> <link title="BatMultiMap" rel="Chapter" href="BatMultiMap.html"> <link title="BatMultiPMap" rel="Chapter" href="BatMultiPMap.html"> <link title="BatMutex" rel="Chapter" href="BatMutex.html"> <link title="BatNativeint" rel="Chapter" href="BatNativeint.html"> <link title="BatNum" rel="Chapter" href="BatNum.html"> <link title="BatNumber" rel="Chapter" href="BatNumber.html"> <link title="BatOo" rel="Chapter" href="BatOo.html"> <link title="BatOptParse" rel="Chapter" href="BatOptParse.html"> <link title="BatOption" rel="Chapter" href="BatOption.html"> <link title="BatOrd" rel="Chapter" href="BatOrd.html"> <link title="BatParserCo" rel="Chapter" href="BatParserCo.html"> <link title="BatPathGen" rel="Chapter" href="BatPathGen.html"> <link title="BatPervasives" rel="Chapter" href="BatPervasives.html"> <link title="BatPrintexc" rel="Chapter" href="BatPrintexc.html"> <link title="BatPrintf" rel="Chapter" href="BatPrintf.html"> <link title="BatQueue" rel="Chapter" href="BatQueue.html"> <link title="BatRMutex" rel="Chapter" href="BatRMutex.html"> <link title="BatRandom" rel="Chapter" href="BatRandom.html"> <link title="BatRef" rel="Chapter" href="BatRef.html"> <link title="BatRefList" rel="Chapter" href="BatRefList.html"> <link title="BatResult" rel="Chapter" href="BatResult.html"> <link title="BatReturn" rel="Chapter" href="BatReturn.html"> <link title="BatScanf" rel="Chapter" href="BatScanf.html"> <link title="BatSeq" rel="Chapter" href="BatSeq.html"> <link title="BatSet" rel="Chapter" href="BatSet.html"> <link title="BatSplay" rel="Chapter" href="BatSplay.html"> <link title="BatStack" rel="Chapter" href="BatStack.html"> <link title="BatStream" rel="Chapter" href="BatStream.html"> <link title="BatString" rel="Chapter" href="BatString.html"> <link title="BatSubstring" rel="Chapter" href="BatSubstring.html"> <link title="BatSys" rel="Chapter" href="BatSys.html"> <link title="BatText" rel="Chapter" href="BatText.html"> <link title="BatTuple" rel="Chapter" href="BatTuple.html"> <link title="BatUChar" rel="Chapter" href="BatUChar.html"> <link title="BatUTF8" rel="Chapter" href="BatUTF8.html"> <link title="BatUnit" rel="Chapter" href="BatUnit.html"> <link title="BatUnix" rel="Chapter" href="BatUnix.html"> <link title="BatUref" rel="Chapter" href="BatUref.html"> <link title="BatVect" rel="Chapter" href="BatVect.html"> <link title="Batteries" rel="Chapter" href="Batteries.html"> <link title="BatteriesConfig" rel="Chapter" href="BatteriesConfig.html"> <link title="BatteriesPrint" rel="Chapter" href="BatteriesPrint.html"> <link title="BatteriesThread" rel="Chapter" href="BatteriesThread.html"> <link title="Extlib" rel="Chapter" href="Extlib.html"><link title="Extending to other languages" rel="Section" href="#6_Extendingtootherlanguages"> <title>Batteries user guide : BatGenlex</title> </head> <body> <div class="navbar"><a class="pre" href="BatGc.html" title="BatGc">Previous</a> <a class="up" href="index.html" title="Index">Up</a> <a class="post" href="BatGlobal.html" title="BatGlobal">Next</a> </div> <h1>Module <a href="type_BatGenlex.html">BatGenlex</a></h1> <pre><span class="keyword">module</span> BatGenlex: <code class="code"><span class="keyword">sig</span></code> <a href="BatGenlex.html">..</a> <code class="code"><span class="keyword">end</span></code></pre><div class="info module top"> A generic lexical analyzer. <p> This module implements a simple ``standard'' lexical analyzer, presented as a function from character streams to token streams. It implements roughly the lexical conventions of OCaml, but is parameterized by the set of keywords of your language. <p> Example: a lexer suitable for a desk calculator is obtained by <pre class="codepre"><code class="code"> <span class="keyword">let</span> lexer = make_lexer [<span class="string">"+"</span>;<span class="string">"-"</span>;<span class="string">"*"</span>;<span class="string">"/"</span>;<span class="string">"let"</span>;<span class="string">"="</span>; <span class="string">"("</span>; <span class="string">")"</span>] </code></pre> <p> The associated parser would be a function from <code class="code">token stream</code> to, for instance, <code class="code">int</code>, and would have rules such as: <p> <pre class="codepre"><code class="code"> <span class="keyword">let</span> parse_expr = <span class="keyword">parser</span><br> [< <span class="keywordsign">'</span><span class="constructor">Int</span> n >] <span class="keywordsign">-></span> n<br> <span class="keywordsign">|</span> [< <span class="keywordsign">'</span><span class="constructor">Kwd</span> <span class="string">"("</span>; n = parse_expr; <span class="keywordsign">'</span><span class="constructor">Kwd</span> <span class="string">")"</span> >] <span class="keywordsign">-></span> n<br> <span class="keywordsign">|</span> [< n1 = parse_expr; n2 = parse_remainder n1 >] <span class="keywordsign">-></span> n2<br> <span class="keyword">and</span> parse_remainder n1 = <span class="keyword">parser</span><br> [< <span class="keywordsign">'</span><span class="constructor">Kwd</span> <span class="string">"+"</span>; n2 = parse_expr >] <span class="keywordsign">-></span> n1+n2<br> <span class="keywordsign">|</span> ...<br> </code></pre><br> <b>Author(s):</b> Jacques Garrigue, David Teller<br> </div> <hr width="100%"> <pre><span id="TYPEtoken"><span class="keyword">type</span> <code class="type"></code>token</span> = <code class="type">Genlex.token</code> = </pre><table class="typetable"> <tr> <td align="left" valign="top" > <code><span class="keyword">|</span></code></td> <td align="left" valign="top" > <code><span id="TYPEELTtoken.Kwd"><span class="constructor">Kwd</span></span> <span class="keyword">of</span> <code class="type">string</code></code></td> </tr> <tr> <td align="left" valign="top" > <code><span class="keyword">|</span></code></td> <td align="left" valign="top" > <code><span id="TYPEELTtoken.Ident"><span class="constructor">Ident</span></span> <span class="keyword">of</span> <code class="type">string</code></code></td> </tr> <tr> <td align="left" valign="top" > <code><span class="keyword">|</span></code></td> <td align="left" valign="top" > <code><span id="TYPEELTtoken.Int"><span class="constructor">Int</span></span> <span class="keyword">of</span> <code class="type">int</code></code></td> </tr> <tr> <td align="left" valign="top" > <code><span class="keyword">|</span></code></td> <td align="left" valign="top" > <code><span id="TYPEELTtoken.Float"><span class="constructor">Float</span></span> <span class="keyword">of</span> <code class="type">float</code></code></td> </tr> <tr> <td align="left" valign="top" > <code><span class="keyword">|</span></code></td> <td align="left" valign="top" > <code><span id="TYPEELTtoken.String"><span class="constructor">String</span></span> <span class="keyword">of</span> <code class="type">string</code></code></td> </tr> <tr> <td align="left" valign="top" > <code><span class="keyword">|</span></code></td> <td align="left" valign="top" > <code><span id="TYPEELTtoken.Char"><span class="constructor">Char</span></span> <span class="keyword">of</span> <code class="type">char</code></code></td> </tr></table> <div class="info "> The type of tokens. The lexical classes are: <code class="code"><span class="constructor">Int</span></code> and <code class="code"><span class="constructor">Float</span></code> for integer and floating-point numbers; <code class="code"><span class="constructor">String</span></code> for string literals, enclosed in double quotes; <code class="code"><span class="constructor">Char</span></code> for character literals, enclosed in single quotes; <code class="code"><span class="constructor">Ident</span></code> for identifiers (either sequences of letters, digits, underscores and quotes, or sequences of ``operator characters'' such as <code class="code">+</code>, <code class="code">*</code>, etc); and <code class="code"><span class="constructor">Kwd</span></code> for keywords (either identifiers or single ``special characters'' such as <code class="code">(</code>, <code class="code">}</code>, etc).<br> </div> <pre><span id="VALmake_lexer"><span class="keyword">val</span> make_lexer</span> : <code class="type">string list -> char Stream.t -> <a href="BatGenlex.html#TYPEtoken">token</a> Stream.t</code></pre><div class="info "> Construct the lexer function. The first argument is the list of keywords. An identifier <code class="code">s</code> is returned as <code class="code"><span class="constructor">Kwd</span> s</code> if <code class="code">s</code> belongs to this list, and as <code class="code"><span class="constructor">Ident</span> s</code> otherwise. A special character <code class="code">s</code> is returned as <code class="code"><span class="constructor">Kwd</span> s</code> if <code class="code">s</code> belongs to this list, and cause a lexical error (exception <code class="code"><span class="constructor">Parse_error</span></code>) otherwise. Blanks and newlines are skipped. Comments delimited by <code class="code">(*</code> and <code class="code">*)</code> are skipped as well, and can be nested.<br> </div> <pre><code><span id="TYPElexer_error"><span class="keyword">type</span> <code class="type"></code>lexer_error</span> = </code></pre><table class="typetable"> <tr> <td align="left" valign="top" > <code><span class="keyword">|</span></code></td> <td align="left" valign="top" > <code><span id="TYPEELTlexer_error.IllegalCharacter"><span class="constructor">IllegalCharacter</span></span> <span class="keyword">of</span> <code class="type">char</code></code></td> </tr> <tr> <td align="left" valign="top" > <code><span class="keyword">|</span></code></td> <td align="left" valign="top" > <code><span id="TYPEELTlexer_error.NotReallyAChar"><span class="constructor">NotReallyAChar</span></span></code></td> </tr> <tr> <td align="left" valign="top" > <code><span class="keyword">|</span></code></td> <td align="left" valign="top" > <code><span id="TYPEELTlexer_error.NotReallyAnEscape"><span class="constructor">NotReallyAnEscape</span></span></code></td> </tr> <tr> <td align="left" valign="top" > <code><span class="keyword">|</span></code></td> <td align="left" valign="top" > <code><span id="TYPEELTlexer_error.EndOfStream"><span class="constructor">EndOfStream</span></span></code></td> </tr></table> <pre><span id="EXCEPTIONLexerError"><span class="keyword">exception</span> LexerError</span> <span class="keyword">of</span> <code class="type"><a href="BatGenlex.html#TYPElexer_error">lexer_error</a> * int</code></pre> <pre><span id="TYPEt"><span class="keyword">type</span> <code class="type"></code>t</span> </pre> <div class="info "> A lexer<br> </div> <pre><span id="VALof_list"><span class="keyword">val</span> of_list</span> : <code class="type">string list -> <a href="BatGenlex.html#TYPEt">t</a></code></pre><div class="info "> Create a lexer from a list of keywords<br> </div> <pre><span id="VALto_stream_filter"><span class="keyword">val</span> to_stream_filter</span> : <code class="type"><a href="BatGenlex.html#TYPEt">t</a> -> char Stream.t -> <a href="BatGenlex.html#TYPEtoken">token</a> Stream.t</code></pre><div class="info "> Apply the lexer to a stream.<br> </div> <pre><span id="VALto_enum_filter"><span class="keyword">val</span> to_enum_filter</span> : <code class="type"><a href="BatGenlex.html#TYPEt">t</a> -> char <a href="BatEnum.html#TYPEt">BatEnum.t</a> -> <a href="BatGenlex.html#TYPEtoken">token</a> <a href="BatEnum.html#TYPEt">BatEnum.t</a></code></pre><div class="info "> Apply the lexer to an enum.<br> </div> <pre><span id="VALto_lazy_list_filter"><span class="keyword">val</span> to_lazy_list_filter</span> : <code class="type"><a href="BatGenlex.html#TYPEt">t</a> -> char <a href="BatLazyList.html#TYPEt">BatLazyList.t</a> -> <a href="BatGenlex.html#TYPEtoken">token</a> <a href="BatLazyList.html#TYPEt">BatLazyList.t</a></code></pre><div class="info "> Apply the lexer to a lazy list.<br> </div> <pre><span id="VALstring_of_token"><span class="keyword">val</span> string_of_token</span> : <code class="type"><a href="BatGenlex.html#TYPEtoken">token</a> -> string</code></pre><br> <h6 id="6_Extendingtootherlanguages">Extending to other languages</h6><br> <pre><span class="keyword">module</span> <a href="BatGenlex.Languages.html">Languages</a>: <code class="code"><span class="keyword">sig</span></code> <a href="BatGenlex.Languages.html">..</a> <code class="code"><span class="keyword">end</span></code></pre></body></html>