[Tarantool-patches] [PATCH v2 2/2] json: print context in error mesages

[Roman Khabibov]

Context is just a string with a few characters before and after
wrong token, wrong token itself and a symbolic arrow pointing to
this token.

Closes #4339
---
 test/app-tap/json.test.lua        | 20 +++++++++-
 third_party/lua-cjson/lua_cjson.c | 62 ++++++++++++++++++++++++++++---
 2 files changed, 76 insertions(+), 6 deletions(-)

diff --git a/test/app-tap/json.test.lua b/test/app-tap/json.test.lua
index 6d511e686..70e9f6cf7 100755
--- a/test/app-tap/json.test.lua
+++ b/test/app-tap/json.test.lua
@@ -22,7 +22,7 @@ end
 
 tap.test("json", function(test)
     local serializer = require('json')
-    test:plan(51)
+    test:plan(57)
 
     test:test("unsigned", common.test_unsigned, serializer)
     test:test("signed", common.test_signed, serializer)
@@ -184,4 +184,22 @@ tap.test("json", function(test)
     test:ok(string.find(err_msg, 'comma') ~= nil, 'comma instead of T_COMMA')
     _, err_msg = pcall(serializer.decode, '{')
     test:ok(string.find(err_msg, 'end') ~= nil, 'end instead of T_END')
+
+    --
+    -- gh-4339: Make sure that context is printed.
+    --
+    _, err_msg = pcall(serializer.decode, '{{: "world"}')
+    test:ok(string.find(err_msg, '{ >> {: "worl') ~= nil, 'context #1')
+    _, err_msg = pcall(serializer.decode, '{"a": "world"}}')
+    test:ok(string.find(err_msg, '"world"} >> }') ~= nil, 'context #2')
+    _, err_msg = pcall(serializer.decode, '{1: "world"}')
+    test:ok(string.find(err_msg, '{ >> 1: "worl') ~= nil, 'context #3')
+    _, err_msg = pcall(serializer.decode, '{')
+    test:ok(string.find(err_msg, '{ >> ') ~= nil, 'context #4')
+    _, err_msg = pcall(serializer.decode, '}')
+    test:ok(string.find(err_msg, ' >> }') ~= nil, 'context #5')
+    serializer.cfg{decode_max_depth = 1}
+    _, err_msg = pcall(serializer.decode, '{"a": {a = {}}}')
+    test:ok(string.find(err_msg, '{"a":  >> {a = {}}') ~= nil, 'context #6')
+
 end)
diff --git a/third_party/lua-cjson/lua_cjson.c b/third_party/lua-cjson/lua_cjson.c
index e68b52847..655d6550e 100644
--- a/third_party/lua-cjson/lua_cjson.c
+++ b/third_party/lua-cjson/lua_cjson.c
@@ -825,6 +825,50 @@ static void json_next_token(json_parse_t *json, json_token_t *token)
     json_set_token_error(token, json, "invalid token");
 }
 
+enum context_length {
+    CONTEXT_ARROW_LENGTH = 4,
+    CONTEXT_MAX_LENGTH_BEFORE = 8,
+    CONTEXT_MAX_LENGTH_AFTER = 8,
+    CONTEXT_MAX_LENGTH = CONTEXT_MAX_LENGTH_BEFORE + CONTEXT_MAX_LENGTH_AFTER +
+    CONTEXT_ARROW_LENGTH,
+};
+
+/**
+ * Copy characters near wrong token with the position @a
+ * column_index to a static string buffer @a context and lay out
+ * arrow " >> " before this token.
+ *
+ * @param context      String static buffer to fill.
+ * @param json         Structure with pointers to parsing string.
+ * @param column_index Position of wrong token in the current
+ *                     line.
+ */
+static void fill_context(char *context, json_parse_t *json, int column_index)
+{
+    assert(column_index >= 0);
+    int length_before = column_index < CONTEXT_MAX_LENGTH_BEFORE ?
+        column_index : CONTEXT_MAX_LENGTH_BEFORE;
+    const char *src = json->cur_line_ptr + column_index - length_before;
+    int i = 0;
+    /* Fill context before the arrow. */
+    for (; i < length_before; i++)
+        context[i] = src[i];
+
+    /* Make the arrow. */
+    context[i] = ' ';
+    memset(context + i + 1, '>', CONTEXT_ARROW_LENGTH - 2);
+    context[i + CONTEXT_ARROW_LENGTH - 1] = ' ';
+
+    /* Fill context after the arrow. */
+    for (int n = 0; n < CONTEXT_MAX_LENGTH_AFTER && src[i] != '\0' &&
+         src[i] != '\n'; i++) {
+        context[i + CONTEXT_ARROW_LENGTH] = src[i];
+        n++;
+    }
+    assert(i + CONTEXT_ARROW_LENGTH <= CONTEXT_MAX_LENGTH);
+    context[i + CONTEXT_ARROW_LENGTH] = '\0';
+}
+
 /* This function does not return.
  * DO NOT CALL WITH DYNAMIC MEMORY ALLOCATED.
  * The only supported exception is the temporary parser string
@@ -843,9 +887,14 @@ static void json_throw_parse_error(lua_State *l, json_parse_t *json,
     else
         found = json_token_type_name[token->type];
 
+    int column_index = token->column_index;
+    char context[CONTEXT_MAX_LENGTH + 1];
+    fill_context(context, json, column_index);
+
     /* Note: token->column_index is 0 based, display starting from 1 */
-    luaL_error(l, "Expected %s but found %s on line %d at character %d", exp,
-               found, json->line_count, token->column_index + 1);
+    luaL_error(l, "Expected %s but found %s on line %d at character %d here "
+               "'%s'", exp, found, json->line_count, token->column_index + 1,
+               context);
 }
 
 static inline void json_decode_ascend(json_parse_t *json)
@@ -862,10 +911,13 @@ static void json_decode_descend(lua_State *l, json_parse_t *json, int slots)
         return;
     }
 
+    char context[CONTEXT_MAX_LENGTH + 1];
+    fill_context(context, json, json->ptr - json->cur_line_ptr - 1);
+
     strbuf_free(json->tmp);
-    luaL_error(l, "Found too many nested data structures (%d) on line %d at "
-               "character %d", json->current_depth, json->line_count,
-               json->ptr - json->cur_line_ptr);
+    luaL_error(l, "Found too many nested data structures (%d) on line %d at cha"
+               "racter %d here '%s'", json->current_depth, json->line_count,
+               json->ptr - json->cur_line_ptr, context);
 }
 
 static void json_parse_object_context(lua_State *l, json_parse_t *json)
-- 
2.21.0 (Apple Git-122)