Test reentering parser for nested inner parses

spec/parse_inner_nested.c.propane

@@ -0,0 +1,19 @@
+<<
+#include <stdlib.h>
+#include <string.h>
+size_t mylexfn(p_context_t * context, p_token_info_t * out_token_info);
+>>
+
+ptype int;
+
+lex_fn mylexfn;
+
+drop /\s+/;
+token lparen /\(/;
+token rparen /\)/;
+token plus /\+/;
+token num /\d+/ << char b[32]; memcpy(b, match, match_length); b[match_length] = '\0'; $$ = atoi(b); >>
+
+Start -> Expr << $$ = $1; >>
+Expr -> num << $$ = $1; >>
+Expr -> Expr plus num << $$ = $1 + $3; >>

spec/parse_inner_nested.d.propane

@@ -0,0 +1,17 @@
+<<
+import test_parse_inner_nested;
+>>
+
+ptype int;
+
+lex_fn mylexfn;
+
+drop /\s+/;
+token lparen /\(/;
+token rparen /\)/;
+token plus /\+/;
+token num /\d+/ << int n = 0; foreach (ch; match) { n *= 10; n += (ch - '0'); } $$ = n; >>
+
+Start -> Expr << $$ = $1; >>
+Expr -> num << $$ = $1; >>
+Expr -> Expr plus num << $$ = $1 + $3; >>

spec/parse_inner_nested_tree.c.propane

@@ -0,0 +1,17 @@
+<<
+size_t mylexfn(p_context_t * context, p_token_info_t * out_token_info);
+>>
+
+tree;
+
+lex_fn mylexfn;
+
+drop /\s+/;
+token lparen /\(/;
+token rparen /\)/;
+token plus /\+/;
+token num /\d+/;
+
+Start -> Expr;
+Expr -> num;
+Expr -> Expr plus num;

spec/parse_inner_nested_tree.d.propane

@@ -0,0 +1,17 @@
+<<
+import test_parse_inner_nested_tree;
+>>
+
+tree;
+
+lex_fn mylexfn;
+
+drop /\s+/;
+token lparen /\(/;
+token rparen /\)/;
+token plus /\+/;
+token num /\d+/;
+
+Start -> Expr;
+Expr -> num;
+Expr -> Expr plus num;

spec/propane_spec.rb

@@ -1686,6 +1686,26 @@ EOF
         expect(results.status).to eq 0
       end
 
+      it "supports a reentrant nested parse driven from a custom lex function" do
+        ext = language == "cpp" ? "c" : language
+        write_grammar(File.read("spec/parse_inner_nested.#{ext}.propane"))
+        run_propane(language: language)
+        compile("spec/test_parse_inner_nested.#{language}", language: language)
+        results = run_test(language: language)
+        expect(results.stderr).to eq ""
+        expect(results.status).to eq 0
+      end
+
+      it "tracks positions across a lex-function nested parse in tree mode" do
+        ext = language == "cpp" ? "c" : language
+        write_grammar(File.read("spec/parse_inner_nested_tree.#{ext}.propane"))
+        run_propane(language: language)
+        compile("spec/test_parse_inner_nested_tree.#{language}", language: language)
+        results = run_test(language: language)
+        expect(results.stderr).to eq ""
+        expect(results.status).to eq 0
+      end
+
       it "allows multiple starting rules in tree mode" do
     write_grammar <<EOF
 tree;

spec/test_parse_inner_nested.c

@@ -0,0 +1,78 @@
+#include "testparser.h"
+#include <assert.h>
+#include <string.h>
+#include "testutils.h"
+
+/* Grammar (integer evaluator; parentheses handled by the lex function):
+ *   ptype int;
+ *   lex_fn mylexfn;
+ *   token lparen /\(/; token rparen /\)/; token plus /\+/;
+ *   token num /\d+/          << ... atoi ... >>
+ *   Start -> Expr            << $$ = $1; >>
+ *   Expr  -> num             << $$ = $1; >>
+ *   Expr  -> Expr plus num   << $$ = $1 + $3; >>
+ *
+ * The tokens lparen and rparen appear in no grammar rule. Instead, when the
+ * lex function lexes a '(', it performs a nested parse (p_parse_inner_Start)
+ * of the parenthesized sub-expression -- reentrantly, while the outer parse is
+ * still suspended in this callback -- reads the computed value with
+ * p_result_Start, consumes the ')' that p_parse_inner deliberately left in the
+ * input, and hands a single synthesized num token carrying that value back to
+ * the outer parse. Nested groups recurse this process to arbitrary depth. */
+
+size_t mylexfn(p_context_t * context, p_token_info_t * out_token_info)
+{
+    size_t result = p_lex(context, out_token_info);
+    if (result != P_SUCCESS)
+    {
+        return result;
+    }
+    if (out_token_info->token == TOKEN_lparen)
+    {
+        /* Nested parse of the parenthesized sub-expression, stopping at the
+         * closing ')' follow token. This re-enters the parser while the outer
+         * parse is suspended in this lex callback. */
+        p_token_t follow_tokens[] = { TOKEN_rparen };
+        size_t inner_result = p_parse_inner_Start(context, follow_tokens, 1u);
+        if (inner_result != P_SUCCESS)
+        {
+            return inner_result;
+        }
+        int value = p_result_Start(context);
+        /* p_parse_inner rewound the input so that ')' was not consumed; consume
+         * it now. */
+        p_token_info_t rparen_info;
+        size_t rparen_result = p_lex(context, &rparen_info);
+        assert(rparen_result == P_SUCCESS);
+        assert(rparen_info.token == TOKEN_rparen);
+        /* Replace the '(' token with a synthesized num carrying the nested
+         * parse result. */
+        out_token_info->token = TOKEN_num;
+        out_token_info->pvalue.v_default = value;
+    }
+    return P_SUCCESS;
+}
+
+static int eval(char const * input)
+{
+    p_context_t * context = p_context_new((uint8_t const *)input, strlen(input));
+    assert(p_parse(context) == P_SUCCESS);
+    int value = p_result(context);
+    p_context_delete(context);
+    return value;
+}
+
+int main()
+{
+    /* No parentheses: plain outer parse. */
+    assert_eq(5u, (size_t)eval("2 + 3"));
+    /* A single group evaluated by the nested parse. */
+    assert_eq(3u, (size_t)eval("(1 + 2)"));
+    /* A group in the middle of an outer expression. */
+    assert_eq(14u, (size_t)eval("2 + (3 + 4) + 5"));
+    /* Nested groups: the nested parse re-enters itself. */
+    assert_eq(37u, (size_t)eval("2 + (10 + (20 + 5))"));
+    assert_eq(15u, (size_t)eval("(1 + 2) + (3 + (4 + 5))"));
+
+    return 0;
+}

spec/test_parse_inner_nested.d

@@ -0,0 +1,64 @@
+import testparser;
+import testutils;
+
+/* Grammar: see test_parse_inner_nested.c. */
+
+size_t mylexfn(p_context_t * context, p_token_info_t * out_token_info)
+{
+    size_t result = p_lex(context, out_token_info);
+    if (result != P_SUCCESS)
+    {
+        return result;
+    }
+    if (out_token_info.token == TOKEN_lparen)
+    {
+        /* Nested parse of the parenthesized sub-expression, stopping at the
+         * closing ')' follow token. This re-enters the parser while the outer
+         * parse is suspended in this lex callback. */
+        p_token_t[] follow_tokens = [TOKEN_rparen];
+        size_t inner_result = p_parse_inner_Start(context, follow_tokens);
+        if (inner_result != P_SUCCESS)
+        {
+            return inner_result;
+        }
+        int value = p_result_Start(context);
+        /* p_parse_inner rewound the input so that ')' was not consumed; consume
+         * it now. */
+        p_token_info_t rparen_info;
+        size_t rparen_result = p_lex(context, &rparen_info);
+        assert(rparen_result == P_SUCCESS);
+        assert(rparen_info.token == TOKEN_rparen);
+        /* Replace the '(' token with a synthesized num carrying the nested
+         * parse result. */
+        out_token_info.token = TOKEN_num;
+        out_token_info.pvalue.v_default = value;
+    }
+    return P_SUCCESS;
+}
+
+int eval(string input)
+{
+    p_context_t * context = p_context_new(input);
+    assert(p_parse(context) == P_SUCCESS);
+    int value = p_result(context);
+    p_context_delete(context);
+    return value;
+}
+
+int main()
+{
+    return 0;
+}
+
+unittest
+{
+    /* No parentheses: plain outer parse. */
+    assert_eq(5, eval("2 + 3"));
+    /* A single group evaluated by the nested parse. */
+    assert_eq(3, eval("(1 + 2)"));
+    /* A group in the middle of an outer expression. */
+    assert_eq(14, eval("2 + (3 + 4) + 5"));
+    /* Nested groups: the nested parse re-enters itself. */
+    assert_eq(37, eval("2 + (10 + (20 + 5))"));
+    assert_eq(15, eval("(1 + 2) + (3 + (4 + 5))"));
+}

spec/test_parse_inner_nested_tree.c

@@ -0,0 +1,104 @@
+#include "testparser.h"
+#include <assert.h>
+#include <string.h>
+#include "testutils.h"
+
+/* Grammar (tree generation mode; parentheses handled by the lex function):
+ *   tree;
+ *   lex_fn mylexfn;
+ *   token lparen /\(/; token rparen /\)/; token plus /\+/; token num /\d+/;
+ *   Start -> Expr;
+ *   Expr  -> num;
+ *   Expr  -> Expr plus num;
+ *
+ * The same lexer-driven nested parse as test_parse_inner_nested, but in tree
+ * generation mode. Each "( ... )" group is parsed by a reentrant
+ * p_parse_inner_Start() call from the lex function; the resulting subtree is
+ * discarded and a single synthesized num token is handed to the outer parse.
+ * The synthesized token's position is set to span the whole group ('(' start
+ * through ')' end), so this verifies that positions survive the nested-parse
+ * boundary and land correctly in the outer tree. */
+
+size_t mylexfn(p_context_t * context, p_token_info_t * out_token_info)
+{
+    size_t result = p_lex(context, out_token_info);
+    if (result != P_SUCCESS)
+    {
+        return result;
+    }
+    if (out_token_info->token == TOKEN_lparen)
+    {
+        p_position_t start_position = out_token_info->position;
+        /* Reentrant nested parse of the parenthesized sub-expression. */
+        p_token_t follow_tokens[] = { TOKEN_rparen };
+        size_t inner_result = p_parse_inner_Start(context, follow_tokens, 1u);
+        if (inner_result != P_SUCCESS)
+        {
+            return inner_result;
+        }
+        Start * inner = p_result_Start(context);
+        assert_not_null(inner);
+        /* p_parse_inner rewound the input so that ')' was not consumed; consume
+         * it now. */
+        p_token_info_t rparen_info;
+        size_t rparen_result = p_lex(context, &rparen_info);
+        assert(rparen_result == P_SUCCESS);
+        assert(rparen_info.token == TOKEN_rparen);
+        /* The subtree covers the region strictly between the parentheses. */
+        assert_eq((size_t)(start_position.col + 1u), (size_t)inner->position.col);
+        assert_eq((size_t)(rparen_info.position.col - 1u), (size_t)inner->end_position.col);
+        p_tree_delete_Start(inner);
+        /* Synthesize a num token spanning the entire "( ... )" group. */
+        out_token_info->token = TOKEN_num;
+        out_token_info->position = start_position;
+        out_token_info->end_position = rparen_info.end_position;
+    }
+    return P_SUCCESS;
+}
+
+int main()
+{
+    /* "(3 + 4) + (5 + 6)": two parenthesized groups, each collapsed by the
+     * lexer into a single num token spanning its group. */
+    char const * input = "(3 + 4) + (5 + 6)";
+    p_context_t * context = p_context_new((uint8_t const *)input, strlen(input));
+    assert(p_parse(context) == P_SUCCESS);
+
+    Start * tree = p_result(context);
+    assert_not_null(tree);
+
+    /* Start -> Expr, where the top Expr is "Expr plus num". */
+    Expr * top = tree->pExpr;
+    assert_not_null(top);
+    assert_not_null(top->pExpr);
+    assert_not_null(top->pToken2);
+    assert_not_null(top->pToken3);
+
+    /* The '+' joining the two groups is at column 9. */
+    assert_eq(1u, (size_t)top->pToken2->position.row);
+    assert_eq(9u, (size_t)top->pToken2->position.col);
+
+    /* Right operand: synthesized num for "(5 + 6)", spanning columns 11..17. */
+    assert_eq(1u, (size_t)top->pToken3->position.row);
+    assert_eq(11u, (size_t)top->pToken3->position.col);
+    assert_eq(1u, (size_t)top->pToken3->end_position.row);
+    assert_eq(17u, (size_t)top->pToken3->end_position.col);
+
+    /* Left operand: Expr -> num, the synthesized num for "(3 + 4)", spanning
+     * columns 1..7. */
+    Expr * left = top->pExpr;
+    assert_not_null(left->pToken1);
+    assert_eq(1u, (size_t)left->pToken1->position.row);
+    assert_eq(1u, (size_t)left->pToken1->position.col);
+    assert_eq(1u, (size_t)left->pToken1->end_position.row);
+    assert_eq(7u, (size_t)left->pToken1->end_position.col);
+
+    /* The whole tree spans columns 1..17. */
+    assert_eq(1u, (size_t)tree->position.col);
+    assert_eq(17u, (size_t)tree->end_position.col);
+
+    p_tree_delete(tree);
+    p_context_delete(context);
+
+    return 0;
+}

spec/test_parse_inner_nested_tree.d

@@ -0,0 +1,91 @@
+import testparser;
+import testutils;
+
+/* Grammar: see test_parse_inner_nested_tree.c. */
+
+size_t mylexfn(p_context_t * context, p_token_info_t * out_token_info)
+{
+    size_t result = p_lex(context, out_token_info);
+    if (result != P_SUCCESS)
+    {
+        return result;
+    }
+    if (out_token_info.token == TOKEN_lparen)
+    {
+        p_position_t start_position = out_token_info.position;
+        /* Reentrant nested parse of the parenthesized sub-expression. */
+        p_token_t[] follow_tokens = [TOKEN_rparen];
+        size_t inner_result = p_parse_inner_Start(context, follow_tokens);
+        if (inner_result != P_SUCCESS)
+        {
+            return inner_result;
+        }
+        Start * inner = p_result_Start(context);
+        assert(inner !is null);
+        /* p_parse_inner rewound the input so that ')' was not consumed; consume
+         * it now. */
+        p_token_info_t rparen_info;
+        size_t rparen_result = p_lex(context, &rparen_info);
+        assert(rparen_result == P_SUCCESS);
+        assert(rparen_info.token == TOKEN_rparen);
+        /* The subtree covers the region strictly between the parentheses. */
+        assert_eq(start_position.col + 1u, inner.position.col);
+        assert_eq(rparen_info.position.col - 1u, inner.end_position.col);
+        p_tree_delete_Start(inner);
+        /* Synthesize a num token spanning the entire "( ... )" group. */
+        out_token_info.token = TOKEN_num;
+        out_token_info.position = start_position;
+        out_token_info.end_position = rparen_info.end_position;
+    }
+    return P_SUCCESS;
+}
+
+int main()
+{
+    return 0;
+}
+
+unittest
+{
+    /* "(3 + 4) + (5 + 6)": two parenthesized groups, each collapsed by the
+     * lexer into a single num token spanning its group. */
+    string input = "(3 + 4) + (5 + 6)";
+    p_context_t * context = p_context_new(input);
+    assert(p_parse(context) == P_SUCCESS);
+
+    Start * tree = p_result(context);
+    assert(tree !is null);
+
+    /* Start -> Expr, where the top Expr is "Expr plus num". */
+    Expr * top = tree.pExpr;
+    assert(top !is null);
+    assert(top.pExpr !is null);
+    assert(top.pToken2 !is null);
+    assert(top.pToken3 !is null);
+
+    /* The '+' joining the two groups is at column 9. */
+    assert_eq(1u, top.pToken2.position.row);
+    assert_eq(9u, top.pToken2.position.col);
+
+    /* Right operand: synthesized num for "(5 + 6)", spanning columns 11..17. */
+    assert_eq(1u, top.pToken3.position.row);
+    assert_eq(11u, top.pToken3.position.col);
+    assert_eq(1u, top.pToken3.end_position.row);
+    assert_eq(17u, top.pToken3.end_position.col);
+
+    /* Left operand: Expr -> num, the synthesized num for "(3 + 4)", spanning
+     * columns 1..7. */
+    Expr * left = top.pExpr;
+    assert(left.pToken1 !is null);
+    assert_eq(1u, left.pToken1.position.row);
+    assert_eq(1u, left.pToken1.position.col);
+    assert_eq(1u, left.pToken1.end_position.row);
+    assert_eq(7u, left.pToken1.end_position.col);
+
+    /* The whole tree spans columns 1..17. */
+    assert_eq(1u, tree.position.col);
+    assert_eq(17u, tree.end_position.col);
+
+    p_tree_delete(tree);
+    p_context_delete(context);
+}