httpie-cli/httpie/output/lexers/json.py
Mickaël Schoentgen e6c5cd3e4b
Improve JSON output when there is leading data before the actual JSON body (#1130)
In some special cases, to prevent against Cross Site Script Inclusion (XSSI)
attacks, the JSON response body starts with a magic prefix line that must be
stripped before feeding the rest of the response body to the JSON parser.
Such prefix is now simply ignored from the parser but still printed in the
terminal.

* Fix Windows tests
2021-09-21 11:15:43 +02:00

32 lines
852 B
Python

import re
from pygments.lexer import bygroups, using, RegexLexer
from pygments.lexers.data import JsonLexer
from pygments.token import Token
PREFIX_TOKEN = Token.Error
PREFIX_REGEX = r'[^{\["]+'
class EnhancedJsonLexer(RegexLexer):
"""
Enhanced JSON lexer for Pygments.
It adds support for eventual data prefixing the actual JSON body.
"""
name = 'JSON'
flags = re.IGNORECASE | re.DOTALL
tokens = {
'root': [
# Eventual non-JSON data prefix followed by actual JSON body.
# FIX: data prefix + number (integer or float) are not correctly handled.
(
fr'({PREFIX_REGEX})' + r'((?:[{\["]|true|false|null).+)',
bygroups(PREFIX_TOKEN, using(JsonLexer))
),
# JSON body.
(r'.+', using(JsonLexer)),
],
}