add config support

2026-07-30 13:18:41 +02:00
parent 215ed9705e
commit dc1aa5e5b6
124 changed files with 7402 additions and 8 deletions
@@ -0,0 +1,2 @@
+/driver
+/out
@@ -0,0 +1,21 @@
+CFLAGS := -O0 -g -fsanitize=address,undefined -std=c17 -Wmissing-declarations -Wall -Wextra -MMD 
+
+all: driver
+
+driver: scanvalue.c
+	$(CC) $(CFLAGS) -o $@ scanvalue.c -lm
+
+test: all
+	bash run.sh
+
+-include driver.d
+
+clean:
+	rm -f *.o *.d driver
+
+distclean: clean
+
+format:
+	clang-format -i *.[ch]
+
+.PHONY: all clean distclean format test
@@ -0,0 +1,16 @@
+= """
+Roses are red
+Violets are blue"""
+
+# On a Unix system, the above multi-line string will most likely be the same as:
+= "Roses are red\nViolets are blue"
+
+# On a Windows system, it will most likely be equivalent to:
+= "Roses are red\r\nViolets are blue"
+
+= """Here are two quotation marks: "". Simple enough."""
+= """Here are three quotation marks: ""\"."""
+= """Here are fifteen quotation marks: ""\"""\"""\"""\"""\"."""
+
+# "This," she said, "is just a pointless statement."
+= """"This," she said, "is just a pointless statement.""""# What you see is what you get.
@@ -0,0 +1,12 @@
+
+# integers
+ = [ 1, 2, 3 ]
+
+# colors
+ = [ "red", "yellow", "green" ]
+
+# nested
+ = [ [ 1, 2 ], [3, 4, 5] ]
+ = [ [ 1, 2 ], ["a", "b", "c"] ]
+ = [ "all", 'strings', """are the same""", '''type''' ]
+
@@ -0,0 +1,6 @@
+# Mixed-type arrays are allowed
+= [ 0.1, 0.2, 0.5, 1.0, 2, 5 ]
+ = [
+  "Foo Bar <foo@example.com>",
+  { }
+]
@@ -0,0 +1,11 @@
+
+# multiline
+ = [
+  1, 2, 3
+]
+
+# extra comma at end
+ = [
+  1,
+  2, # this is ok
+]
@@ -0,0 +1,2 @@
+
+ = { }
@@ -0,0 +1,17 @@
+# all results are the same
+
+= "abc"
+
+= """
+a\
+
+
+         b\
+           c"""
+
+= """\
+              a\
+              b\
+              c\
+              """
+
@@ -0,0 +1,9 @@
+# line-ending backslash with whitespace "geeee\  "
+# result should be "heeee\ngeeee"
+
+= """
+heeee
+geeee\  
+
+
+             """
@@ -0,0 +1,2 @@
+= "\t tab tab tab \t"
+= "\e There is no escape! \e"
@@ -0,0 +1 @@
+= inf
@@ -0,0 +1,4 @@
+
+ = 2023-01-01T12:34:56.123456789Z
+ = 2023-01-01T12:34:56.123456789
+ = 07:32:00.123456789
@@ -0,0 +1,11 @@
+= 'C:\Users\nodejs\templates'
+= '\\ServerX\admin$\system32\'
+= 'Tom "Dubs" Preston-Werner'
+= '<\i\c*\s*>'
+= '''I [dw]on't need \d{2} apples'''
+= '''
+The first newline is
+trimmed in raw strings.
+   All other whitespace
+   is preserved.
+'''
@@ -0,0 +1,7 @@
+ = '''Here are fifteen quotation marks: """""""""""""""'''
+
+# apos15 = '''Here are fifteen apostrophes: ''''''''''''''''''  # INVALID
+ = "Here are fifteen apostrophes: '''''''''''''''"
+
+# 'That,' she said, 'is still pointless.'
+ = ''''That,' she said, 'is still pointless.''''
@@ -0,0 +1,10 @@
+
+ = "pi"
+ = +99
+ = 42
+ = 0
+ = -17
+ = 1_000
+ = 5_349_221
+ = 53_49_221  # Indian number system grouping
+ = 1_2_3_4_5  # VALID but discouraged
@@ -0,0 +1,11 @@
+# hexadecimal with prefix `0x`
+ = 0xDEADBEEF
+ = 0xdeadbeef
+ = 0xdead_beef
+
+# octal with prefix `0o`
+ = 0o01234567
+ = 0o755 # useful for Unix file permissions
+
+# binary with prefix `0b`
+ = 0b11010110
@@ -0,0 +1,15 @@
+
+# fractional
+ = +1.0
+ = 3.1415
+ = -0.01
+
+# exponent
+ = 5e+22
+ = 1e06
+ = -2E-2
+
+# both
+ = 6.626e-34
+
+ = 224_617.445_991_228
@@ -0,0 +1,10 @@
+
+# infinity
+ = inf  # positive infinity
+ = +inf # positive infinity
+ = -inf # negative infinity
+
+# not a number
+ = nan  # actual sNaN/qNaN encoding is implementation-specific
+ = +nan # same as `nan`
+ = -nan # valid, actual encoding is implementation-specific
@@ -0,0 +1,3 @@
+
+ = true
+ = false
@@ -0,0 +1,13 @@
+
+ = 1979-05-27T07:32:00Z
+ = 1979-05-27T00:32:00-07:00
+ = 1979-05-27T00:32:00.999999-07:00
+ = 1979-05-27 07:32:00Z
+ = 1979-05-27T07:32:00
+ = 1979-05-27T00:32:00.999999
+= 1979-05-27
+= 07:32:00
+= 00:32:00.999999
+
+# lower
+ = 1987-07-05t17:45:00z
@@ -0,0 +1,2 @@
+# trailing .
+= 1997-09-09T09:09:09.
@@ -0,0 +1,2 @@
+# timezone offset overflow minute
+= 1985-06-18 17:04:07+12:60
@@ -0,0 +1,20 @@
+#!/bin/bash
+mkdir -p out
+
+echo
+echo =========================
+echo == scanvalue test
+echo =========================
+
+for fname in {1..100} e{1..100}; do
+    IN="in/$fname"
+    if [ -f $IN ]; then
+        echo test $fname
+	OUT="out/$fname.out"
+	GOOD="good/$fname.out"
+        ./driver $IN &> $OUT
+        diff $GOOD $OUT || { echo '--- FAILED ---'; exit 1; }
+    fi
+done
+
+echo DONE
@@ -0,0 +1,161 @@
+#include "../../src/tomlc17.c"
+#include <inttypes.h>
+#include <stdlib.h>
+
+const char **g_argv = 0;
+int g_argc = 0;
+
+static void usage() {
+  fprintf(stderr, "Usage: %s fname\n", g_argv[0]);
+  exit(1);
+}
+
+static void printspecial(const char *p, int n) {
+  for (int i = 0; i < n; i++, p++) {
+    int ch = (*p == '\n') ? '_' : *p;
+    putchar(ch);
+  }
+}
+
+static const char *fmt_double(double f, char *buf, int buflen) {
+  snprintf(buf, buflen, "%.16g", f);
+  if (!strchr(buf, 'e') && !strchr(buf, '.') && !strchr(buf, 'n')) {
+    // add a .0 if the number is an int, and not inf or nan.
+    snprintf(buf, buflen, "%.16g%s", f, ".0");
+  }
+  if (isnan(f) && signbit(f)) {
+    snprintf(buf, buflen, "%s", "-nan");
+  }
+  return buf;
+}
+
+static void printtok(char *content, const token_t tok) {
+  // clang-format off
+#define CASESTR(x) case TOK_ ## x: s = #x; break
+  // clang-format on
+  char *s = 0;
+  switch (tok.toktyp) {
+    CASESTR(DOT);
+    CASESTR(EQUAL);
+    CASESTR(COMMA);
+    CASESTR(LBRACK);
+    CASESTR(RBRACK);
+    CASESTR(LBRACE);
+    CASESTR(RBRACE);
+    CASESTR(STRING);
+    CASESTR(MLSTRING);
+    CASESTR(LITSTRING);
+    CASESTR(MLLITSTRING);
+    CASESTR(TIME);
+    CASESTR(DATE);
+    CASESTR(DATETIME);
+    CASESTR(DATETIMETZ);
+    CASESTR(INTEGER);
+    CASESTR(FLOAT);
+    CASESTR(BOOL);
+    CASESTR(LIT);
+    CASESTR(ENDL);
+    CASESTR(FIN);
+  default:
+    s = "UNKNOWN";
+    break;
+  }
+  printf("%s %ld %d ", s, tok.str.ptr - content, tok.str.len);
+  printspecial(tok.str.ptr, tok.str.len);
+
+  char buf[50];
+  switch (tok.toktyp) {
+  case TOK_INTEGER:
+    printf(" %" PRId64, tok.u.int64);
+    break;
+  case TOK_FLOAT:
+    printf(" %s", fmt_double(tok.u.fp64, buf, sizeof(buf)));
+    break;
+  case TOK_BOOL:
+    printf(" %s", tok.u.b1 ? "true" : "false");
+    break;
+  default:
+    break;
+  }
+  printf("\n");
+}
+
+static char *readfile(const char *fname, int *ret_len) {
+  FILE *fp = fopen(fname, "r");
+  if (!fp) {
+    perror("fopen");
+    exit(1);
+  }
+
+  // Seek to the end of the file to determine its size
+  if (fseek(fp, 0, SEEK_END) != 0) {
+    perror("fseek");
+    exit(1);
+  }
+
+  long file_size = ftell(fp);
+  if (file_size == -1) {
+    perror("ftell");
+    exit(1);
+  }
+  rewind(fp); // Go back to the beginning of the file
+
+  // Allocate memory for the file content, plus one for the null terminator
+  char *content = malloc(file_size + 1);
+  if (!content) {
+    perror("out of memory");
+    exit(1);
+  }
+
+  // Read the file into the buffer
+  size_t read_size = fread(content, 1, file_size, fp);
+  if (read_size != (size_t)file_size) {
+    perror("fread");
+    exit(1);
+  }
+  content[file_size] = '\0'; // Null-terminate the string
+  fclose(fp);
+
+  *ret_len = file_size;
+  return content;
+}
+
+int main(int argc, const char *argv[]) {
+  g_argc = argc;
+  g_argv = argv;
+  if (argc != 2) {
+    usage();
+  }
+  int len;
+  char *content = readfile(argv[1], &len);
+  char errbuf[200];
+
+  scanner_t scanner;
+  scanner_t *sp = &scanner;
+  scan_init(sp, content, len, errbuf, sizeof(errbuf));
+
+  for (;;) {
+    (void)scan_key; // silent compiler
+    token_t tok;
+    if (scan_value(sp, &tok)) {
+      printf("%s\n", errbuf);
+      goto bail;
+    }
+    if (tok.toktyp == TOK_FIN) {
+      break;
+    }
+    printtok(content, tok);
+  }
+
+  if (sp->errmsg) {
+    printf("ERROR: %s (line %d)\n", sp->errmsg, sp->lineno);
+    goto bail;
+  }
+
+  free(content);
+  return 0;
+
+bail:
+  free(content);
+  return 1;
+}