Add status check before parsing the json string
This is related to the issue https://github.com/nlmatics/llmsherpa/issues/64.
The root cause of this issue is that the client does not check the response status and try to parse the non-json content returned from the server. Since this status error is not directly shown to users, users only see the json parsing exception.
With this patch, users will see the raw content from the server
```
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
File <timed exec>:5
File ~/miniconda3/envs/py11/lib/python3.11/site-packages/llmsherpa/readers/file_reader.py:73, in LayoutPDFReader.read_pdf(self, path_or_url, contents)
71 parser_response = self._parse_pdf(pdf_file)
72 if parser_response.status > 200:
---> 73 raise ValueError(f"{[parser_response.data](http://parser_response.data/)}")
74 response_json = json.loads(parser_response.data.decode("utf-8"))
75 blocks = response_json['return_dict']['result']['blocks']
ValueError: b'<html>\r\n<head><title>403 Forbidden</title></head>\r\n<body>\r\n<center><h1>403 Forbidden</h1></center>\r\n<hr><center>nginx</center>\r\n</body>\r\n</html>\r\n'
```
Instead of the implicit one:
```
--------------------------------------------------------------------------
JSONDecodeError Traceback (most recent call last)
File <timed exec>:5
File ~/miniconda3/envs/py11/lib/python3.11/site-packages/llmsherpa/readers/file_reader.py:72, in LayoutPDFReader.read_pdf(self, path_or_url, contents)
70 pdf_file = (file_name, file_data, 'application/pdf')
71 parser_response = self._parse_pdf(pdf_file)
---> 72 response_json = json.loads(parser_response.data.decode("utf-8"))
73 blocks = response_json['return_dict']['result']['blocks']
74 return Document(blocks)
File ~/miniconda3/envs/py11/lib/python3.11/json/__init__.py:346, in loads(s, cls, object_hook, parse_float, parse_int, parse_constant, object_pairs_hook, **kw)
341 s = s.decode(detect_encoding(s), 'surrogatepass')
343 if (cls is None and object_hook is None and
344 parse_int is None and parse_float is None and
345 parse_constant is None and object_pairs_hook is None and not kw):
--> 346 return _default_decoder.decode(s)
347 if cls is None:
348 cls = JSONDecoder
File ~/miniconda3/envs/py11/lib/python3.11/json/decoder.py:337, in JSONDecoder.decode(self, s, _w)
332 def decode(self, s, _w=WHITESPACE.match):
333 """Return the Python representation of ``s`` (a ``str`` instance
334 containing a JSON document).
335
336 """
--> 337 obj, end = self.raw_decode(s, idx=_w(s, 0).end())
338 end = _w(s, end).end()
339 if end != len(s):
File ~/miniconda3/envs/py11/lib/python3.11/json/decoder.py:355, in JSONDecoder.raw_decode(self, s, idx)
353 obj, end = self.scan_once(s, idx)
354 except StopIteration as err:
--> 355 raise JSONDecodeError("Expecting value", s, err.value) from None
356 return obj, end
JSONDecodeError: Expecting value: line 1 column 1 (char 0)
```
合并状态:未合并 关闭于 2024-05-06 1 条评论