about summary refs log tree commit diff
path: root/src/libexpr/lexer.l
diff options
context:
space:
mode:
Diffstat (limited to 'src/libexpr/lexer.l')
-rw-r--r--src/libexpr/lexer.l193
1 files changed, 193 insertions, 0 deletions
diff --git a/src/libexpr/lexer.l b/src/libexpr/lexer.l
new file mode 100644
index 000000000000..82520ee7a59a
--- /dev/null
+++ b/src/libexpr/lexer.l
@@ -0,0 +1,193 @@
+%option reentrant bison-bridge bison-locations
+%option noyywrap
+%option never-interactive
+
+
+%x STRING
+%x IND_STRING
+
+
+%{
+#include "nixexpr.hh"
+#include "parser-tab.hh"
+
+using namespace nix;
+
+namespace nix {
+
+
+static void initLoc(YYLTYPE * loc)
+{
+    loc->first_line = loc->last_line = 1;
+    loc->first_column = loc->last_column = 1;
+}
+
+
+static void adjustLoc(YYLTYPE * loc, const char * s, size_t len)
+{
+    loc->first_line = loc->last_line;
+    loc->first_column = loc->last_column;
+
+    while (len--) {
+       switch (*s++) {
+       case '\r':
+           if (*s == '\n') /* cr/lf */
+               s++;
+           /* fall through */
+       case '\n':
+           ++loc->last_line;
+           loc->last_column = 1;
+           break;
+       default:
+           ++loc->last_column;
+       }
+    }
+}
+
+
+static Expr * unescapeStr(SymbolTable & symbols, const char * s)
+{
+    string t;
+    char c;
+    while ((c = *s++)) {
+        if (c == '\\') {
+            assert(*s);
+            c = *s++;
+            if (c == 'n') t += '\n';
+            else if (c == 'r') t += '\r';
+            else if (c == 't') t += '\t';
+            else t += c;
+        }
+        else if (c == '\r') {
+            /* Normalise CR and CR/LF into LF. */
+            t += '\n';
+            if (*s == '\n') s++; /* cr/lf */
+        }
+        else t += c;
+    }
+    return new ExprString(symbols.create(t));
+}
+
+
+}
+
+#define YY_USER_INIT initLoc(yylloc)
+#define YY_USER_ACTION adjustLoc(yylloc, yytext, yyleng);
+
+%}
+
+
+ID          [a-zA-Z\_][a-zA-Z0-9\_\'\-]*
+INT         [0-9]+
+PATH        [a-zA-Z0-9\.\_\-\+]*(\/[a-zA-Z0-9\.\_\-\+]+)+
+SPATH       \<[a-zA-Z0-9\.\_\-\+]+(\/[a-zA-Z0-9\.\_\-\+]+)*\>
+URI         [a-zA-Z][a-zA-Z0-9\+\-\.]*\:[a-zA-Z0-9\%\/\?\:\@\&\=\+\$\,\-\_\.\!\~\*\']+
+
+
+%%
+
+
+if          { return IF; }
+then        { return THEN; }
+else        { return ELSE; }
+assert      { return ASSERT; }
+with        { return WITH; }
+let         { return LET; }
+in          { return IN; }
+rec         { return REC; }
+inherit     { return INHERIT; }
+or          { return OR_KW; }
+\.\.\.      { return ELLIPSIS; }
+
+\=\=        { return EQ; }
+\!\=        { return NEQ; }
+\<\=        { return LEQ; }
+\>\=        { return GEQ; }
+\&\&        { return AND; }
+\|\|        { return OR; }
+\-\>        { return IMPL; }
+\/\/        { return UPDATE; }
+\+\+        { return CONCAT; }
+
+{ID}        { yylval->id = strdup(yytext); return ID; }
+{INT}       { errno = 0;
+              yylval->n = strtol(yytext, 0, 10);
+              if (errno != 0)
+                  throw ParseError(format("invalid integer ‘%1%’") % yytext);
+              return INT;
+            }
+
+\$\{        { return DOLLAR_CURLY; }
+
+\"          { BEGIN(STRING); return '"'; }
+<STRING>([^\$\"\\]|\$[^\{\"]|\\.)+ {
+              /* !!! Not quite right: we want a follow restriction on
+                 "$", it shouldn't be followed by a "{".  Right now
+                 "$\"" will be consumed as part of a string, rather
+                 than a "$" followed by the string terminator.
+                 Disallow "$\"" for now. */
+              yylval->e = unescapeStr(data->symbols, yytext);
+              return STR;
+            }
+<STRING>\$\{  { BEGIN(INITIAL); return DOLLAR_CURLY; }
+<STRING>\"  { BEGIN(INITIAL); return '"'; }
+<STRING>.   return yytext[0]; /* just in case: shouldn't be reached */
+
+\'\'(\ *\n)?     { BEGIN(IND_STRING); return IND_STRING_OPEN; }
+<IND_STRING>([^\$\']|\$[^\{\']|\'[^\'\$])+ {
+                   yylval->e = new ExprIndStr(yytext);
+                   return IND_STR;
+                 }
+<IND_STRING>\'\'\$ {
+                   yylval->e = new ExprIndStr("$");
+                   return IND_STR;
+                 }
+<IND_STRING>\'\'\' {
+                   yylval->e = new ExprIndStr("''");
+                   return IND_STR;
+                 }
+<IND_STRING>\'\'\\. {
+                   yylval->e = unescapeStr(data->symbols, yytext + 2);
+                   return IND_STR;
+                 }
+<IND_STRING>\$\{ { BEGIN(INITIAL); return DOLLAR_CURLY; }
+<IND_STRING>\'\' { BEGIN(INITIAL); return IND_STRING_CLOSE; }
+<IND_STRING>\'   {
+                   yylval->e = new ExprIndStr("'");
+                   return IND_STR;
+                 }
+<IND_STRING>.    return yytext[0]; /* just in case: shouldn't be reached */
+
+{PATH}      { yylval->path = strdup(yytext); return PATH; }
+{SPATH}     { yylval->path = strdup(yytext); return SPATH; }
+{URI}       { yylval->uri = strdup(yytext); return URI; }
+
+[ \t\r\n]+    /* eat up whitespace */
+\#[^\r\n]*    /* single-line comments */
+\/\*([^*]|\*[^\/])*\*\/  /* long comments */
+
+.           return yytext[0];
+
+
+%%
+
+
+namespace nix {
+
+/* Horrible, disgusting hack: allow the parser to set the scanner
+   start condition back to STRING.  Necessary in interpolations like
+   "foo${expr}bar"; after the close brace we have to go back to the
+   STRING state. */
+void backToString(yyscan_t scanner)
+{
+    struct yyguts_t * yyg = (struct yyguts_t *) scanner;
+    BEGIN(STRING);
+}
+
+void backToIndString(yyscan_t scanner)
+{
+    struct yyguts_t * yyg = (struct yyguts_t *) scanner;
+    BEGIN(IND_STRING);
+}
+
+}