First pass at string interpolation.

Requires a lexer hack, but a surprisingly un-hideous one. The lexer
maintains a stack of bracket characters so that it can match
parens/brackets/braces to tell where a subexp nested in a string
actually ends.

2 files changed, 98 insertions, 2 deletions

diff --git a/c/lexer.l b/c/lexer.l
index dd93f497..94196146 100644
--- a/c/lexer.l
+++ b/c/lexer.l
@@ -11,11 +11,23 @@
 
 %}
 
+%s IN_PAREN
+%s IN_BRACKET
+%s IN_BRACE
+%s IN_QQINTERP
+%x IN_QQSTRING
+%{
+  static int enter(int opening, int state, yyscan_t yyscanner);
+  static int try_exit(int closing, int state, yyscan_t yyscanner);
+%}
+
 %option noyywrap nounput noinput nodefault
 %option reentrant
 %option extra-type="int"
 %option bison-bridge bison-locations
 %option prefix="jq_yy"
+%option stack
+
 
 %%
 
@@ -37,7 +49,16 @@
 "*=" { return SETMULT; }
 "/=" { return SETDIV; }
 "//=" { return SETDEFINEDOR; }
-"."|"="|";"|"["|"]"|","|":"|"("|")"|"{"|"}"|"|"|"+"|"-"|"*"|"/"|"\$" { return yytext[0];}
+"."|"="|";"|","|":"|"|"|"+"|"-"|"*"|"/"|"\$" { return yytext[0];}
+
+"["|"{"|"(" {
+  return enter(yytext[0], YY_START, yyscanner);
+}
+
+"]"|"}"|")" {
+  return try_exit(yytext[0], YY_START, yyscanner);
+}
+
 
 \"(\\.|[^\\\"])*\" |
 -?[0-9.]+([eE][+-]?[0-9]+)? { 
@@ -48,6 +69,25 @@
   yylval->literal = jv_invalid_with_msg(jv_string("Unterminated string"));
   return LITERAL;
 }
+
+"@(" {
+  yy_push_state(IN_QQSTRING, yyscanner);
+  return QQSTRING_START;
+}
+
+<IN_QQSTRING>{
+  "%(" {
+    return enter(QQSTRING_INTERP_START, YY_START, yyscanner);
+  }
+  [a-z]+ {
+    yylval->literal = jv_string_sized(yytext, yyleng);
+    return QQSTRING_TEXT;
+  }
+  ")" {
+    yy_pop_state(yyscanner);
+    return QQSTRING_END;
+  }
+}
   
 
 [[:alnum:]]+  { yylval->literal = jv_string(yytext); return IDENT;}
@@ -63,3 +103,38 @@
 "false" { return FALSE; }
 "null" { return NULL; }
 */
+static int try_exit(int c, int state, yyscan_t yyscanner) {
+  char match = 0;
+  int ret;
+  switch (state) {
+  case IN_PAREN: match = ret = ')'; break;
+  case IN_BRACKET: match = ret = ']'; break;
+  case IN_BRACE: match = ret = '}'; break;
+
+  case IN_QQINTERP:
+    match = ')'; 
+    ret = QQSTRING_INTERP_END;
+    break;
+  }
+  assert(match);
+  if (match == c) {
+    yy_pop_state(yyscanner);
+    return ret;
+  } else {
+    // FIXME: should we pop? Give a better error at least
+    return INVALID_CHARACTER;
+  }
+}
+
+static int enter(int c, int currstate, yyscan_t yyscanner) {
+  int state = 0;
+  switch (c) {
+  case '(': state = IN_PAREN; break;
+  case '[': state = IN_BRACKET; break;
+  case '{': state = IN_BRACE; break;
+  case QQSTRING_INTERP_START: state = IN_QQINTERP; break;
+  }
+  assert(state);
+  yy_push_state(state, yyscanner);
+  return c;
+}
diff --git a/c/parser.y b/c/parser.y
index d8780a87..2684a26e 100644
--- a/c/parser.y
+++ b/c/parser.y
@@ -61,6 +61,12 @@
 %token SETDIV "/="
 %token SETDEFINEDOR "//="
 
+%token QQSTRING_START
+%token <literal> QQSTRING_TEXT
+%token QQSTRING_INTERP_START
+%token QQSTRING_INTERP_END
+%token QQSTRING_END
+
  /* revolting hack */
 %left ';'
 %left '|'
@@ -74,7 +80,7 @@
 %left '*' '/'
 
 
-%type <blk> Exp Term MkDict MkDictPair ExpD ElseBody
+%type <blk> Exp Term MkDict MkDictPair ExpD ElseBody QQString
 %{
 #include "lexer.yy.h"
 #define FAIL(loc, msg)                                   \
@@ -264,11 +270,26 @@ Exp "==" Exp {
   $$ = gen_binop($1, $3, EQ);
 } |
 
+QQSTRING_START QQString QQSTRING_END {
+  $$ = $2;
+} |
+
 Term { 
   $$ = $1; 
 }
 
 
+QQString:
+/* empty */ {
+  $$ = gen_op_const(LOADK, jv_string(""));
+} |
+QQString QQSTRING_TEXT {
+  $$ = gen_binop($1, gen_op_const(LOADK, $2), '+');
+} |
+QQString QQSTRING_INTERP_START Exp QQSTRING_INTERP_END {
+  $$ = gen_binop($1, $3, '+');
+}
+
 
 ElseBody:
 "elif" Exp "then" Exp ElseBody {