File size: 7,502 Bytes
8207382
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
# Copyright (c) 2026 PaddlePaddle Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

import os
from typing import Optional, Union

from ._core import (
    default_payload,
    job_id_for_task,
    resolve_document_model,
    resolve_document_options,
    resolve_ocr_model,
    validate_input_source,
)
from ._http import DEFAULT_BASE_URL, HTTPClient
from ._poller import Poller, parse_doc_parsing_result, parse_ocr_result
from ._resources import (
    save_document_parsing_result_resources,
    save_ocr_result_resources,
    save_resource,
)
from .errors import AuthError
from .models import (
    DocParsingOptions,
    Model,
    OCROptions,
)
from .results import BatchStatus, DocParsingResult, Job, JobStatus, OCRResult


class PaddleOCRClient:
    """Synchronous blocking client for PaddleOCR official API.

    Wraps the async job API internally: submit → poll → fetch result.
    """

    def __init__(
        self,
        token: Optional[str] = None,
        base_url: Optional[str] = None,
        request_timeout: float = 300.0,
        poll_timeout: float = 600.0,
        client_platform: Optional[str] = None,
    ):
        self._token = token or os.environ.get("PADDLEOCR_ACCESS_TOKEN", "")
        if not self._token:
            raise AuthError(
                "Token is required. Set PADDLEOCR_ACCESS_TOKEN or pass token=."
            )
        resolved_base_url = (
            base_url or os.environ.get("PADDLEOCR_BASE_URL") or DEFAULT_BASE_URL
        )
        self._http = HTTPClient(
            self._token,
            resolved_base_url,
            request_timeout,
            client_platform=client_platform,
        )
        self._poller = Poller(self._http, max_wait_time=poll_timeout)

    def __enter__(self):
        return self

    def __exit__(self, *args):
        self.close()

    def close(self):
        self._http.close()

    def ocr(
        self,
        file_url: Optional[str] = None,
        file_path: Optional[str] = None,
        options: Optional[OCROptions] = None,
        page_ranges: Optional[str] = None,
        batch_id: Optional[str] = None,
        model: Union[Model, str] = Model.PP_OCRV6,
    ) -> OCRResult:
        model = resolve_ocr_model(model)
        job_id = self._submit(
            model,
            file_url,
            file_path,
            options,
            page_ranges,
            batch_id,
        )
        jsonl_data, _ = self._poller.poll_until_done(job_id)
        return parse_ocr_result(job_id, jsonl_data)

    def parse_document(
        self,
        model: Union[Model, str] = Model.PADDLE_OCR_VL_16,
        file_url: Optional[str] = None,
        file_path: Optional[str] = None,
        options: Optional[DocParsingOptions] = None,
        page_ranges: Optional[str] = None,
        batch_id: Optional[str] = None,
    ) -> DocParsingResult:
        model = resolve_document_model(model)
        options = resolve_document_options(model, options)
        job_id = self._submit(
            model, file_url, file_path, options, page_ranges, batch_id
        )
        jsonl_data, _ = self._poller.poll_until_done(job_id)
        return parse_doc_parsing_result(job_id, jsonl_data)

    def submit_ocr(
        self,
        file_url: Optional[str] = None,
        file_path: Optional[str] = None,
        options: Optional[OCROptions] = None,
        page_ranges: Optional[str] = None,
        batch_id: Optional[str] = None,
        model: Union[Model, str] = Model.PP_OCRV6,
    ) -> Job:
        model = resolve_ocr_model(model)
        job_id = self._submit(
            model,
            file_url,
            file_path,
            options,
            page_ranges,
            batch_id,
        )
        return Job(job_id=job_id, model=model.value, task="ocr")

    def submit_document_parsing(
        self,
        model: Union[Model, str] = Model.PADDLE_OCR_VL_16,
        file_url: Optional[str] = None,
        file_path: Optional[str] = None,
        options: Optional[DocParsingOptions] = None,
        page_ranges: Optional[str] = None,
        batch_id: Optional[str] = None,
    ) -> Job:
        model = resolve_document_model(model)
        options = resolve_document_options(model, options)
        job_id = self._submit(
            model, file_url, file_path, options, page_ranges, batch_id
        )
        return Job(job_id=job_id, model=model.value, task="document_parsing")

    def wait_ocr_result(self, job: Union[Job, str]) -> OCRResult:
        job_id = job_id_for_task(job, "ocr")
        jsonl_data, _ = self._poller.poll_until_done(job_id)
        return parse_ocr_result(job_id, jsonl_data)

    def wait_document_parsing_result(self, job: Union[Job, str]) -> DocParsingResult:
        job_id = job_id_for_task(job, "document_parsing")
        jsonl_data, _ = self._poller.poll_until_done(job_id)
        return parse_doc_parsing_result(job_id, jsonl_data)

    def get_status(self, job_id: str) -> JobStatus:
        return self._poller.get_status(job_id)

    def get_batch_status(self, batch_id: str) -> BatchStatus:
        return self._poller.get_batch_status(batch_id)

    def save_resource(
        self,
        resource_url: str,
        destination: str,
        *,
        overwrite: bool = False,
        filename: Optional[str] = None,
    ) -> str:
        return save_resource(
            resource_url,
            destination,
            overwrite=overwrite,
            filename=filename,
            timeout=self._http.timeout,
        )

    def save_ocr_result_resources(
        self,
        result: OCRResult,
        destination: str,
        *,
        overwrite: bool = False,
    ) -> list:
        return save_ocr_result_resources(
            result,
            destination,
            overwrite=overwrite,
            timeout=self._http.timeout,
        )

    def save_document_parsing_result_resources(
        self,
        result: DocParsingResult,
        destination: str,
        *,
        overwrite: bool = False,
    ) -> list:
        return save_document_parsing_result_resources(
            result,
            destination,
            overwrite=overwrite,
            timeout=self._http.timeout,
        )

    def _submit(
        self,
        model: Model,
        file_url: Optional[str],
        file_path: Optional[str],
        options,
        page_ranges: Optional[str],
        batch_id: Optional[str],
    ) -> str:
        validate_input_source(file_url, file_path)
        payload = options.to_payload() if options else default_payload(model)
        if file_url:
            return self._http.submit_url(
                model.value,
                file_url,
                payload,
                page_ranges=page_ranges,
                batch_id=batch_id,
            )
        return self._http.submit_file(
            model.value,
            file_path,
            payload,
            page_ranges=page_ranges,
            batch_id=batch_id,
        )