Tarantool development patches archive
 help / color / mirror / Atom feed
From: Roman Khabibov <roman.habibov@tarantool.org>
To: tarantool-patches@dev.tarantool.org
Subject: [Tarantool-patches] [PATCH 2/2] json: print context in error mesages
Date: Fri,  9 Oct 2020 00:59:56 +0300	[thread overview]
Message-ID: <20201008215956.93983-3-roman.habibov@tarantool.org> (raw)
In-Reply-To: <20201008215956.93983-1-roman.habibov@tarantool.org>

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 | 59 ++++++++++++++++++++++++++++---
 2 files changed, 73 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 33cf30577..f9e06172d 100644
--- a/third_party/lua-cjson/lua_cjson.c
+++ b/third_party/lua-cjson/lua_cjson.c
@@ -831,6 +831,48 @@ 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;
+    /* Fill context before the arrow. */
+    memcpy(context, src, length_before);
+    context += length_before;
+    src += length_before;
+
+    /* Make the arrow. */
+    *(context++) = ' ';
+    memset(context, '>', CONTEXT_ARROW_LENGTH - 2);
+    context += CONTEXT_ARROW_LENGTH - 2;
+    *(context++) = ' ';
+
+    /* Fill context after the arrow. */
+    const char *end = context + CONTEXT_MAX_LENGTH_AFTER;
+    for (; context < end && *src != '\0' && *src != '\n'; ++src, ++context)
+        *context = *src;
+    *context = '\0';
+}
+
 /* This function does not return.
  * DO NOT CALL WITH DYNAMIC MEMORY ALLOCATED.
  * The only supported exception is the temporary parser string
@@ -849,9 +891,13 @@ 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, column_index + 1, context);
 }
 
 static inline void json_decode_ascend(json_parse_t *json)
@@ -868,10 +914,13 @@ 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)
-- 
2.24.3 (Apple Git-128)

  parent reply	other threads:[~2020-10-08 22:00 UTC|newest]

Thread overview: 13+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-10-08 21:59 [Tarantool-patches] [PATCH 0/2] Improve json error message Roman Khabibov
2020-10-08 21:59 ` [Tarantool-patches] [PATCH 1/2] json: make error messages more readable Roman Khabibov
2020-10-12  8:52   ` Leonid Vasiliev
2020-10-08 21:59 ` Roman Khabibov [this message]
2020-10-12  9:20   ` [Tarantool-patches] [PATCH 2/2] json: print context in error mesages Leonid Vasiliev
2020-11-03  9:53     ` roman
2020-11-09 21:21       ` Leonid Vasiliev
2020-10-12  8:51 ` [Tarantool-patches] [PATCH 0/2] Improve json error message Leonid Vasiliev
2020-11-03 10:01   ` roman
2020-11-09 21:22     ` Leonid Vasiliev
2020-11-05 15:44       ` roman
2020-11-12 14:03         ` Alexander V. Tikhonov
2020-11-26  9:46 ` Kirill Yukhin

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20201008215956.93983-3-roman.habibov@tarantool.org \
    --to=roman.habibov@tarantool.org \
    --cc=tarantool-patches@dev.tarantool.org \
    --subject='Re: [Tarantool-patches] [PATCH 2/2] json: print context in error mesages' \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox