tests: add new fuzzer

Signed-off-by: David Korczynski <david@adalogics.com>

1 files changed, 297 insertions, 0 deletions

diff --git a/tests/jq_fuzz_fixed.cpp b/tests/jq_fuzz_fixed.cpp
new file mode 100644
index 00000000..3dd955bb
--- /dev/null
+++ b/tests/jq_fuzz_fixed.cpp
@@ -0,0 +1,297 @@
+#include <fuzzer/FuzzedDataProvider.h>
+#include <string>
+
+#include "jq.h"
+#include "jv.h"
+
+
+const char *jq_progs[] = {
+    ". / \", \"",
+    ".[]",
+    "$ENV.PAGER",
+    ".[0]",
+    ". < 0.12345678901234567890123456788",
+    ".[] == 1",
+    ".[] | (1 / .)?",
+    "10 / . * 3",
+    "[1,2,empty,3]",
+    "1, empty, 2",
+    "[.,1]|until(.[0] < 1; [.[0] - 1, .[1] * .[0]])|.[1]",
+    ".[-2:]",
+    ".[-2]",
+    ".[2]",
+    "[ .[] | . * 2]",
+    ".[2:4]",
+    "(. + 2) * 5",
+    ".[:3]",
+    ".[4,2]",
+    "42 and \"a string\"",
+    "4 - .a",
+    ". < 5",
+    ".. | .a?",
+    "[.[] | .a?]",
+    ".a + 1",
+    "{a: 1} + {b: 2} + {c: 3} + {a: 42}",
+    ".a + .b",
+    ".a = .b",
+    ".a |= .b",
+    "add",
+    "all",
+    ".a + null",
+    "any",
+    ".[] as [$a, $b] | {a: $a, b: $b}",
+    ". as [$a, $b, {c: $c}] | $a + $b + $c",
+    ".[] as {$a, $b, c: {$d}} ?// {$a, $b, c: [{$e}]} | {$a, $b, $d, $e}",
+    ".[] as {$a, $b, c: {$d, $e}} ?// {$a, $b, c: [{$d, $e}]} | {$a, $b, "
+    "$d, $e}",
+    ".[] as [$a] ?// [$b] | if $a != null then error(\"err: \($a)\") else "
+    "{$a,$b} end",
+    ". as $big | [$big, $big + 1] | map(. > "
+    "10000000000000000000000000000000)",
+    ". as $dot|fromstream($dot|tostream)|.==$dot",
+    ". as $i|[(.*2|. as $i| $i), $i]",
+    "ascii_upcase",
+    ".bar as $x | .foo | . + $x",
+    "@base64",
+    "@base64d",
+    ". == {\"b\": {\"d\": (4 + 1e-20), \"c\": 3}, \"a\":1}",
+    "bsearch(0)",
+    "bsearch(4) as $ix | if $ix < 0 then .[-(1+$ix)] = 4 else . end",
+    "capture(\"(?<a>[a-z]+)-(?<n>[0-9]+)\")",
+    "capture(\"(?<a>[a-z]+)-(?<n>[0-9]+)\")",
+    "combinations",
+    "combinations(2)",
+    "contains(\"bar\")",
+    "contains([\"baz\", \"bar\"])",
+    "contains([\"bazzzzz\", \"bar\"])",
+    "contains({foo: 12, bar: [{barp: 15}]})",
+    "def addvalue(f): f as $x | map(. + $x); addvalue(.[0])",
+    "def addvalue(f): . + [f]; map(addvalue(.[0]))",
+    "def while(cond; update): def _while: if cond then ., (update | "
+    "_while) else empty end; _while; [while(.<100; .*2)]",
+    "del(.[1, 2])",
+    "del(.foo)",
+    "delpaths([[\"a\",\"b\"]])",
+    "empty // 42",
+    "[.[]|endswith(\"foo\")]",
+    "env.PAGER",
+    "explode",
+    ". == false",
+    "(false, null, 1) // 42",
+    "(false, null, 1) | . // 42",
+    "flatten",
+    "flatten(1)",
+    "floor",
+    ".[\"foo\"]",
+    ".[\"foo\"]?",
+    ".foo",
+    ".foo?",
+    ".foo[]",
+    "[.foo?]",
+    ".foo += 1",
+    ".foo // 42",
+    ".foo, .bar",
+    "foreach .[] as $item (0; . + $item)",
+    "foreach .[] as $item (0; . + $item; [$item, . * 2])",
+    "foreach .[] as $item (0; . + 1; {index: ., $item})",
+    "fromdate",
+    "from_entries",
+    "fromstream(1|truncate_stream([[0],1],[[1,0],2],[[1,0]],[[1]]))",
+    "getpath([\"a\",\"b\"])",
+    "[getpath([\"a\",\"b\"], [\"a\",\"c\"])]",
+    "group_by(.foo)",
+    "[.[] | gsub(\", \"; \":\")]",
+    "gsub(\"$\"; \"a\"; \"g\")",
+    "gsub(\"^\"; \"a\")",
+    "[gsub(\"(?<a>.)\"; \"\(.a|ascii_upcase)\", \"\(.a|ascii_downcase)\", "
+    "\"c\")]",
+    "gsub(\"^.*?a\"; \"b\")",
+    "gsub(\"^.*a\"; \"b\")",
+    "gsub(\"a\";\"b\")",
+    "gsub(\"\"; \"a\"; \"g\")",
+    "gsub(\"\"; \"a\"; \"g\")",
+    "gsub(\"[^a-z]*(?<x>[a-z]*)\"; \"Z\(.x)\")",
+    "gsub(\"\\b(?<x>.)\"; \"\(.x|ascii_downcase)\")",
+    "gsub(\"(?<d>\\d)\"; \":\(.d);\")",
+    "gsub(\"^\"; \"\"; \"g\")",
+    "[gsub(\"p\"; \"a\", \"b\")]",
+    "gsub(\"(?=u)\"; \"u\")",
+    "gsub(\"(.*)\"; \"\"; \"x\")",
+    "gsub(\"(?<x>.)[^a]*\"; \"+\(.x)-\")",
+    "gsub(\"(?<x>.)(?<y>[0-9])\"; \"\(.x|ascii_downcase)\(.y)\")",
+    "@html",
+    "if . == 0 then   \"zero\" elif . == 1 then   \"one\" else   \"many\" "
+    "end",
+    "implode",
+    "index(\", \")",
+    "index(1)",
+    "index([1,2])",
+    "indices(\", \")",
+    "indices(1)",
+    "indices([1,2])",
+    ".[] | (infinite * .) < 0",
+    "infinite, nan | type",
+    ".[] | in({\"foo\": 42})",
+    "inside({\"foo\": 12, \"bar\":[1,2,{\"barp\":12, \"blip\":13}]})",
+    "inside({\"foo\": 12, \"bar\":[1,2,{\"barp\":12, \"blip\":13}]})",
+    "inside(\"foobar\")",
+    "inside([\"foobar\", \"foobaz\", \"blarp\"])",
+    "inside([\"foobar\", \"foobaz\", \"blarp\"])",
+    "isempty(.[])",
+    "isempty(.[])",
+    "isempty(empty)",
+    "join(\" \")",
+    "join(\", \")",
+    "keys",
+    "keys",
+    ".[] | length",
+    "[limit(3;.[])]",
+    "[.[]|ltrimstr(\"foo\")]",
+    "map(., .)",
+    "map(.+1)",
+    "map([., . == 1]) | tojson",
+    "map(abs)",
+    "map(has(2))",
+    "map(has(\"foo\"))",
+    "map(in([0,1]))",
+    "map(select(. >= 2))",
+    "map(type)",
+    "map_values(.+1)",
+    "map_values(. // empty)",
+    "match(\"(abc)+\"; \"g\")",
+    "[match(\"a\"; \"gi\")]",
+    "[match(\".+?\\b\")]",
+    "[match([\"(bar)\"])]",
+    "match(\"foo\")",
+    "[match([\"foo (?<bar123>bar)? foo\", \"ig\"])]",
+    "match(\"foo (?<bar123>bar)? foo\"; \"ig\")",
+    "match([\"foo\", \"ig\"])",
+    "[match(\"\"; \"g\")]",
+    "[ match(\".\"; \"g\")] | length",
+    "[match(\"( )*\"; \"gn\")]",
+    "max_by(.foo)",
+    "min",
+    ".[] | .name",
+    ".[]|numbers",
+    "[path(..)]",
+    "path(.a[0].b)",
+    "[paths]",
+    "[paths(type == \"number\")]",
+    "pick(.[2], .[0], .[0])",
+    "pick(.a, .b.c, .x)",
+    "[range(0; 10; -1)]",
+    "[range(0; 10; 3)]",
+    "[range(0; -5; -1)]",
+    "[range(2; 4)]",
+    "range(2; 4)",
+    "[range(4)]",
+    "[range(.)]|[first, last, nth(5)]",
+    "recurse",
+    "recurse(. * .; . < 20)",
+    "recurse(.foo[])",
+    "reduce .[] as [$i,$j] (0; . + $i * $j)",
+    "reduce .[] as $item (0; . + $item)",
+    "reduce .[] as {$x,$y} (null; .x += $x | .y += [$y])",
+    "[repeat(.*2, error)?]",
+    "reverse",
+    "rindex(\", \")",
+    "rindex(1)",
+    "rindex([1,2])",
+    "[.[]|rtrimstr(\"foo\")]",
+    "[.[] | scan(\", \")]",
+    "[.[] | scan(\"b+\"; \"i\")]",
+    "scan(\"c\")",
+    ".[] | select(.id == \"second\")",
+    "(..|select(type==\"boolean\")) |= if . then 1 else 0 end",
+    "setpath([0,\"a\"]; 1)",
+    "setpath([\"a\",\"b\"]; 1)",
+    "setpath([\"a\",\"b\"]; 1)",
+    "@sh \"echo \(.)\"",
+    "sort",
+    "sort_by(.foo)",
+    "sort_by(.foo, .bar)",
+    "split(\", *\"; null)",
+    "splits(\", *\")",
+    "sqrt",
+    "[.[]|startswith(\"foo\")]",
+    "strptime(\"%Y-%m-%dT%H:%M:%SZ\")",
+    "strptime(\"%Y-%m-%dT%H:%M:%SZ\")|mktime",
+    "[sub(\"(?<a>.)\"; \"\(.a|ascii_upcase)\", \"\(.a|ascii_downcase)\")]",
+    "[sub(\"(?<a>.)\"; \"\(.a|ascii_upcase)\", \"\(.a|ascii_downcase)\", "
+    "\"c\")]",
+    "[sub(\"a\"; \"b\", \"c\")]",
+    "sub(\"[^a-z]*(?<x>[a-z]+)\"; \"Z\(.x)\"; \"g\")",
+    "[.[]|[[sub(\", *\";\":\")], [gsub(\", *\";\":\")], [scan(\", *\")]]]",
+    "[.[]|[[sub(\", +\";\":\")], [gsub(\", +\";\":\")], [scan(\", +\")]]]",
+    "sub(\"^(?<head>.)\"; \"Head=\(.head) Tail=\")",
+    "[test(\"ā\")]",
+    ".[] | test(\"a b c # spaces are ignored\"; \"ix\")",
+    "test(\"foo\")",
+    "to_entries",
+    "[., tojson]",
+    "[.[]|tojson]",
+    "[.[]|tojson|fromjson]",
+    ".[] | tonumber",
+    "[.[] | tonumber?]",
+    ".[] | tostring",
+    "[.[]|tostring]",
+    "transpose",
+    "[true, false | not]",
+    "(true, false) or false",
+    "(true, true) and (true, false)",
+    "truncate_stream([[0],1],[[1,0],2],[[1,0]],[[1]])",
+    "[.[]|try .a]",
+    "unique",
+    "unique_by(.foo)",
+    "unique_by(length)",
+    ".user, .projects[]",
+    "[.user, .projects[]]",
+    "{(.user): .titles}",
+    "{user, title: .titles[]}",
+    "utf8bytelength",
+    "walk(if type == \"array\" then sort else . end)",
+    "walk( if type == \"object\" then with_entries( .key |= sub( \"^_+\"; "
+    "\"\") ) else . end )",
+    "[while(.<100; .*2)]",
+    "with_entries(.key |= \"KEY_\" + .)",
+    ". - [\"xml\", \"yaml\"]",
+};
+
+// Fuzzer inspired by /src/jq_test.c
+// The goal is to have the fuzzer execute the functions:
+// jq_compile -> jv_parse -> jq_next.
+extern "C" int LLVMFuzzerTestOneInput(uint8_t *data, size_t size) {
+  FuzzedDataProvider fdp(data, size);
+  std::string parse_payload1 = fdp.ConsumeRandomLengthString();
+  std::string parse_payload2 = fdp.ConsumeRandomLengthString();
+
+  int idx = fdp.ConsumeIntegralInRange<int>(
+      0, (sizeof(jq_progs) / sizeof(char *)) - 1);
+
+  jq_state *jq = NULL;
+  jq = jq_init();
+  if (jq != NULL) {
+    jq_set_attr(jq, jv_string("JQ_ORIGIN"), jv_string("/tmp/"));
+
+    if (jq_compile(jq, jq_progs[idx])) {
+      // Process to jv_parse and then jv_next
+      jv input = jv_parse(parse_payload1.c_str());
+      if (jv_is_valid(input)) {
+        jq_start(jq, input, 0);
+        jv next = jv_parse(parse_payload2.c_str());
+        if (jv_is_valid(next)) {
+          jv actual = jq_next(jq);
+          jv_free(actual);
+        }
+        jv_free(next);
+      } else {
+        // Only free if input is invalid as otherwise jq_teardown
+        // frees it.
+        jv_free(input);
+      }
+    }
+  }
+  jq_teardown(&jq);
+
+  return 0;
+}