context.dev 2.6.0 → 2.7.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/CHANGELOG.md +10 -0
- data/README.md +1 -1
- data/lib/context_dev/models/batch_cancel_response.rb +70 -183
- data/lib/context_dev/models/batch_list_response.rb +86 -95
- data/lib/context_dev/models/batch_retrieve_response.rb +86 -103
- data/lib/context_dev/models/crawl_controls.rb +126 -0
- data/lib/context_dev/models/failure.rb +27 -0
- data/lib/context_dev/models/intake.rb +62 -0
- data/lib/context_dev/models/{error_count.rb → page_error_count.rb} +1 -1
- data/lib/context_dev/models/web_screenshot_params.rb +5 -7
- data/lib/context_dev/models/web_web_crawl_md_params.rb +5 -7
- data/lib/context_dev/models/web_web_scrape_html_params.rb +5 -7
- data/lib/context_dev/models/web_web_scrape_md_params.rb +5 -7
- data/lib/context_dev/models.rb +6 -2
- data/lib/context_dev/resources/batch.rb +3 -6
- data/lib/context_dev/resources/web.rb +4 -4
- data/lib/context_dev/version.rb +1 -1
- data/lib/context_dev.rb +4 -2
- data/rbi/context_dev/models/batch_cancel_response.rbi +98 -316
- data/rbi/context_dev/models/batch_list_response.rbi +127 -152
- data/rbi/context_dev/models/batch_retrieve_response.rbi +126 -161
- data/rbi/context_dev/models/crawl_controls.rbi +252 -0
- data/rbi/context_dev/models/{error.rbi → failure.rbi} +10 -7
- data/rbi/context_dev/models/intake.rbi +88 -0
- data/rbi/context_dev/models/{error_count.rbi → page_error_count.rbi} +2 -2
- data/rbi/context_dev/models/web_screenshot_params.rbi +6 -9
- data/rbi/context_dev/models/web_web_crawl_md_params.rbi +6 -9
- data/rbi/context_dev/models/web_web_scrape_html_params.rbi +6 -9
- data/rbi/context_dev/models/web_web_scrape_md_params.rbi +6 -9
- data/rbi/context_dev/models.rbi +6 -2
- data/rbi/context_dev/resources/batch.rbi +3 -6
- data/rbi/context_dev/resources/web.rbi +8 -12
- data/sig/context_dev/models/batch_cancel_response.rbs +32 -124
- data/sig/context_dev/models/batch_list_response.rbs +42 -63
- data/sig/context_dev/models/batch_retrieve_response.rbs +42 -70
- data/sig/context_dev/models/crawl_controls.rbs +114 -0
- data/sig/context_dev/models/{error.rbs → failure.rbs} +2 -2
- data/sig/context_dev/models/intake.rbs +40 -0
- data/sig/context_dev/models/{error_count.rbs → page_error_count.rbs} +2 -2
- data/sig/context_dev/models.rbs +6 -2
- metadata +14 -8
- data/lib/context_dev/models/error.rb +0 -26
|
@@ -100,7 +100,15 @@ module ContextDev
|
|
|
100
100
|
sig { returns(String) }
|
|
101
101
|
attr_accessor :id
|
|
102
102
|
|
|
103
|
-
#
|
|
103
|
+
# The crawl controls as submitted, so the limits requested can be compared against
|
|
104
|
+
# what the crawl reached.
|
|
105
|
+
sig { returns(T.nilable(ContextDev::CrawlControls)) }
|
|
106
|
+
attr_reader :crawl
|
|
107
|
+
|
|
108
|
+
sig { params(crawl: T.nilable(ContextDev::CrawlControls::OrHash)).void }
|
|
109
|
+
attr_writer :crawl
|
|
110
|
+
|
|
111
|
+
# What this batch has done to your credit balance.
|
|
104
112
|
sig { returns(ContextDev::Models::BatchListResponse::Data::Credits) }
|
|
105
113
|
attr_reader :credits
|
|
106
114
|
|
|
@@ -112,29 +120,31 @@ module ContextDev
|
|
|
112
120
|
end
|
|
113
121
|
attr_writer :credits
|
|
114
122
|
|
|
115
|
-
#
|
|
116
|
-
|
|
117
|
-
|
|
123
|
+
# A failure of the batch as a whole, distinct from the per-page failures in
|
|
124
|
+
# `page_errors`.
|
|
125
|
+
sig { returns(T.nilable(ContextDev::Failure)) }
|
|
126
|
+
attr_reader :failure
|
|
118
127
|
|
|
119
|
-
sig { params(
|
|
120
|
-
attr_writer :
|
|
128
|
+
sig { params(failure: T.nilable(ContextDev::Failure::OrHash)).void }
|
|
129
|
+
attr_writer :failure
|
|
121
130
|
|
|
122
|
-
#
|
|
123
|
-
|
|
124
|
-
|
|
131
|
+
# What each page is returned as. Matches `input.data.format` on the submit
|
|
132
|
+
# request.
|
|
133
|
+
sig do
|
|
134
|
+
returns(
|
|
135
|
+
ContextDev::Models::BatchListResponse::Data::Format::TaggedSymbol
|
|
136
|
+
)
|
|
137
|
+
end
|
|
138
|
+
attr_accessor :format_
|
|
125
139
|
|
|
126
|
-
#
|
|
127
|
-
sig { returns(ContextDev::
|
|
140
|
+
# What submission took in, and what it charged for.
|
|
141
|
+
sig { returns(ContextDev::Intake) }
|
|
128
142
|
attr_reader :input
|
|
129
143
|
|
|
130
|
-
sig
|
|
131
|
-
params(
|
|
132
|
-
input: ContextDev::Models::BatchListResponse::Data::Input::OrHash
|
|
133
|
-
).void
|
|
134
|
-
end
|
|
144
|
+
sig { params(input: ContextDev::Intake::OrHash).void }
|
|
135
145
|
attr_writer :input
|
|
136
146
|
|
|
137
|
-
# How pages
|
|
147
|
+
# How pages were selected. Matches `input.mode` on the submit request.
|
|
138
148
|
sig do
|
|
139
149
|
returns(
|
|
140
150
|
ContextDev::Models::BatchListResponse::Data::Mode::TaggedSymbol
|
|
@@ -142,7 +152,12 @@ module ContextDev
|
|
|
142
152
|
end
|
|
143
153
|
attr_accessor :mode
|
|
144
154
|
|
|
145
|
-
#
|
|
155
|
+
# Individual page failures grouped by error code, sorted by count. Unrelated to
|
|
156
|
+
# `failure`, which is the batch itself failing.
|
|
157
|
+
sig { returns(T::Array[ContextDev::PageErrorCount]) }
|
|
158
|
+
attr_accessor :page_errors
|
|
159
|
+
|
|
160
|
+
# Pages attempted so far. Use `status` to check completion.
|
|
146
161
|
sig { returns(ContextDev::Models::BatchListResponse::Data::Progress) }
|
|
147
162
|
attr_reader :progress
|
|
148
163
|
|
|
@@ -154,8 +169,8 @@ module ContextDev
|
|
|
154
169
|
end
|
|
155
170
|
attr_writer :progress
|
|
156
171
|
|
|
157
|
-
# Download links available
|
|
158
|
-
# serves the same records as paginated JSON.
|
|
172
|
+
# Download links, available once the batch reaches a final status and null before
|
|
173
|
+
# then. GET /batch/{batch_id}/results serves the same records as paginated JSON.
|
|
159
174
|
sig do
|
|
160
175
|
returns(
|
|
161
176
|
T.nilable(ContextDev::Models::BatchListResponse::Data::Results)
|
|
@@ -195,24 +210,19 @@ module ContextDev
|
|
|
195
210
|
end
|
|
196
211
|
attr_writer :timing
|
|
197
212
|
|
|
198
|
-
# Output format.
|
|
199
|
-
sig do
|
|
200
|
-
returns(
|
|
201
|
-
ContextDev::Models::BatchListResponse::Data::Type::TaggedSymbol
|
|
202
|
-
)
|
|
203
|
-
end
|
|
204
|
-
attr_accessor :type
|
|
205
|
-
|
|
206
213
|
# An asynchronous web scraping job.
|
|
207
214
|
sig do
|
|
208
215
|
params(
|
|
209
216
|
id: String,
|
|
217
|
+
crawl: T.nilable(ContextDev::CrawlControls::OrHash),
|
|
210
218
|
credits:
|
|
211
219
|
ContextDev::Models::BatchListResponse::Data::Credits::OrHash,
|
|
212
|
-
|
|
213
|
-
|
|
214
|
-
|
|
220
|
+
failure: T.nilable(ContextDev::Failure::OrHash),
|
|
221
|
+
format_:
|
|
222
|
+
ContextDev::Models::BatchListResponse::Data::Format::OrSymbol,
|
|
223
|
+
input: ContextDev::Intake::OrHash,
|
|
215
224
|
mode: ContextDev::Models::BatchListResponse::Data::Mode::OrSymbol,
|
|
225
|
+
page_errors: T::Array[ContextDev::PageErrorCount::OrHash],
|
|
216
226
|
progress:
|
|
217
227
|
ContextDev::Models::BatchListResponse::Data::Progress::OrHash,
|
|
218
228
|
results:
|
|
@@ -222,35 +232,40 @@ module ContextDev
|
|
|
222
232
|
status:
|
|
223
233
|
ContextDev::Models::BatchListResponse::Data::Status::OrSymbol,
|
|
224
234
|
tags: T::Array[String],
|
|
225
|
-
timing: ContextDev::Models::BatchListResponse::Data::Timing::OrHash
|
|
226
|
-
type: ContextDev::Models::BatchListResponse::Data::Type::OrSymbol
|
|
235
|
+
timing: ContextDev::Models::BatchListResponse::Data::Timing::OrHash
|
|
227
236
|
).returns(T.attached_class)
|
|
228
237
|
end
|
|
229
238
|
def self.new(
|
|
230
239
|
# Batch ID used to retrieve or cancel the job.
|
|
231
240
|
id:,
|
|
232
|
-
#
|
|
241
|
+
# The crawl controls as submitted, so the limits requested can be compared against
|
|
242
|
+
# what the crawl reached.
|
|
243
|
+
crawl:,
|
|
244
|
+
# What this batch has done to your credit balance.
|
|
233
245
|
credits:,
|
|
234
|
-
#
|
|
235
|
-
|
|
236
|
-
|
|
237
|
-
|
|
238
|
-
#
|
|
246
|
+
# A failure of the batch as a whole, distinct from the per-page failures in
|
|
247
|
+
# `page_errors`.
|
|
248
|
+
failure:,
|
|
249
|
+
# What each page is returned as. Matches `input.data.format` on the submit
|
|
250
|
+
# request.
|
|
251
|
+
format_:,
|
|
252
|
+
# What submission took in, and what it charged for.
|
|
239
253
|
input:,
|
|
240
|
-
# How pages
|
|
254
|
+
# How pages were selected. Matches `input.mode` on the submit request.
|
|
241
255
|
mode:,
|
|
242
|
-
#
|
|
256
|
+
# Individual page failures grouped by error code, sorted by count. Unrelated to
|
|
257
|
+
# `failure`, which is the batch itself failing.
|
|
258
|
+
page_errors:,
|
|
259
|
+
# Pages attempted so far. Use `status` to check completion.
|
|
243
260
|
progress:,
|
|
244
|
-
# Download links available
|
|
245
|
-
# serves the same records as paginated JSON.
|
|
261
|
+
# Download links, available once the batch reaches a final status and null before
|
|
262
|
+
# then. GET /batch/{batch_id}/results serves the same records as paginated JSON.
|
|
246
263
|
results:,
|
|
247
264
|
# Current state. `completed`, `cancelled`, and `failed` are final.
|
|
248
265
|
status:,
|
|
249
266
|
# Tags stored on the batch at submission.
|
|
250
267
|
tags:,
|
|
251
|
-
timing
|
|
252
|
-
# Output format.
|
|
253
|
-
type:
|
|
268
|
+
timing:
|
|
254
269
|
)
|
|
255
270
|
end
|
|
256
271
|
|
|
@@ -258,21 +273,22 @@ module ContextDev
|
|
|
258
273
|
override.returns(
|
|
259
274
|
{
|
|
260
275
|
id: String,
|
|
276
|
+
crawl: T.nilable(ContextDev::CrawlControls),
|
|
261
277
|
credits: ContextDev::Models::BatchListResponse::Data::Credits,
|
|
262
|
-
|
|
263
|
-
|
|
264
|
-
|
|
278
|
+
failure: T.nilable(ContextDev::Failure),
|
|
279
|
+
format_:
|
|
280
|
+
ContextDev::Models::BatchListResponse::Data::Format::TaggedSymbol,
|
|
281
|
+
input: ContextDev::Intake,
|
|
265
282
|
mode:
|
|
266
283
|
ContextDev::Models::BatchListResponse::Data::Mode::TaggedSymbol,
|
|
284
|
+
page_errors: T::Array[ContextDev::PageErrorCount],
|
|
267
285
|
progress: ContextDev::Models::BatchListResponse::Data::Progress,
|
|
268
286
|
results:
|
|
269
287
|
T.nilable(ContextDev::Models::BatchListResponse::Data::Results),
|
|
270
288
|
status:
|
|
271
289
|
ContextDev::Models::BatchListResponse::Data::Status::TaggedSymbol,
|
|
272
290
|
tags: T::Array[String],
|
|
273
|
-
timing: ContextDev::Models::BatchListResponse::Data::Timing
|
|
274
|
-
type:
|
|
275
|
-
ContextDev::Models::BatchListResponse::Data::Type::TaggedSymbol
|
|
291
|
+
timing: ContextDev::Models::BatchListResponse::Data::Timing
|
|
276
292
|
}
|
|
277
293
|
)
|
|
278
294
|
end
|
|
@@ -288,94 +304,83 @@ module ContextDev
|
|
|
288
304
|
)
|
|
289
305
|
end
|
|
290
306
|
|
|
291
|
-
#
|
|
307
|
+
# `reserved` minus `refunded` — what the batch has cost so far. Equal to
|
|
308
|
+
# `reserved` until the batch settles.
|
|
292
309
|
sig { returns(Integer) }
|
|
293
|
-
attr_accessor :
|
|
310
|
+
attr_accessor :net
|
|
294
311
|
|
|
295
|
-
# Credits
|
|
312
|
+
# Credits returned for pages that did not succeed. Stays 0 until the batch reaches
|
|
313
|
+
# a final status, then settles in one movement.
|
|
296
314
|
sig { returns(Integer) }
|
|
297
|
-
attr_accessor :
|
|
315
|
+
attr_accessor :refunded
|
|
298
316
|
|
|
299
|
-
#
|
|
317
|
+
# Credits debited from your balance the moment the batch was accepted. This is a
|
|
318
|
+
# charge, not a forecast — the whole amount leaves the balance up front.
|
|
319
|
+
sig { returns(Integer) }
|
|
320
|
+
attr_accessor :reserved
|
|
321
|
+
|
|
322
|
+
# What this batch has done to your credit balance.
|
|
300
323
|
sig do
|
|
301
|
-
params(
|
|
324
|
+
params(net: Integer, refunded: Integer, reserved: Integer).returns(
|
|
302
325
|
T.attached_class
|
|
303
326
|
)
|
|
304
327
|
end
|
|
305
328
|
def self.new(
|
|
306
|
-
#
|
|
307
|
-
|
|
308
|
-
|
|
309
|
-
|
|
329
|
+
# `reserved` minus `refunded` — what the batch has cost so far. Equal to
|
|
330
|
+
# `reserved` until the batch settles.
|
|
331
|
+
net:,
|
|
332
|
+
# Credits returned for pages that did not succeed. Stays 0 until the batch reaches
|
|
333
|
+
# a final status, then settles in one movement.
|
|
334
|
+
refunded:,
|
|
335
|
+
# Credits debited from your balance the moment the batch was accepted. This is a
|
|
336
|
+
# charge, not a forecast — the whole amount leaves the balance up front.
|
|
337
|
+
reserved:
|
|
310
338
|
)
|
|
311
339
|
end
|
|
312
340
|
|
|
313
|
-
sig
|
|
341
|
+
sig do
|
|
342
|
+
override.returns(
|
|
343
|
+
{ net: Integer, refunded: Integer, reserved: Integer }
|
|
344
|
+
)
|
|
345
|
+
end
|
|
314
346
|
def to_hash
|
|
315
347
|
end
|
|
316
348
|
end
|
|
317
349
|
|
|
318
|
-
|
|
319
|
-
|
|
350
|
+
# What each page is returned as. Matches `input.data.format` on the submit
|
|
351
|
+
# request.
|
|
352
|
+
module Format
|
|
353
|
+
extend ContextDev::Internal::Type::Enum
|
|
354
|
+
|
|
355
|
+
TaggedSymbol =
|
|
320
356
|
T.type_alias do
|
|
321
|
-
T.
|
|
322
|
-
ContextDev::Models::BatchListResponse::Data::Input,
|
|
323
|
-
ContextDev::Internal::AnyHash
|
|
324
|
-
)
|
|
357
|
+
T.all(Symbol, ContextDev::Models::BatchListResponse::Data::Format)
|
|
325
358
|
end
|
|
359
|
+
OrSymbol = T.type_alias { T.any(Symbol, String) }
|
|
326
360
|
|
|
327
|
-
|
|
328
|
-
|
|
329
|
-
|
|
330
|
-
|
|
331
|
-
|
|
332
|
-
|
|
333
|
-
|
|
334
|
-
|
|
335
|
-
|
|
336
|
-
|
|
337
|
-
attr_accessor :invalid
|
|
338
|
-
|
|
339
|
-
# Pages submitted before validation. For a crawl, the page limit.
|
|
340
|
-
sig { returns(Integer) }
|
|
341
|
-
attr_accessor :submitted
|
|
342
|
-
|
|
343
|
-
# Submission counts.
|
|
344
|
-
sig do
|
|
345
|
-
params(
|
|
346
|
-
accepted: Integer,
|
|
347
|
-
duplicates: Integer,
|
|
348
|
-
invalid: Integer,
|
|
349
|
-
submitted: Integer
|
|
350
|
-
).returns(T.attached_class)
|
|
351
|
-
end
|
|
352
|
-
def self.new(
|
|
353
|
-
# Pages accepted, or the crawl page limit. Credits are reserved for this count.
|
|
354
|
-
accepted:,
|
|
355
|
-
# Duplicate URL and `itemId` pairs skipped. Always 0 for crawls.
|
|
356
|
-
duplicates:,
|
|
357
|
-
# Pages rejected during validation.
|
|
358
|
-
invalid:,
|
|
359
|
-
# Pages submitted before validation. For a crawl, the page limit.
|
|
360
|
-
submitted:
|
|
361
|
-
)
|
|
362
|
-
end
|
|
361
|
+
MARKDOWN =
|
|
362
|
+
T.let(
|
|
363
|
+
:markdown,
|
|
364
|
+
ContextDev::Models::BatchListResponse::Data::Format::TaggedSymbol
|
|
365
|
+
)
|
|
366
|
+
HTML =
|
|
367
|
+
T.let(
|
|
368
|
+
:html,
|
|
369
|
+
ContextDev::Models::BatchListResponse::Data::Format::TaggedSymbol
|
|
370
|
+
)
|
|
363
371
|
|
|
364
372
|
sig do
|
|
365
373
|
override.returns(
|
|
366
|
-
|
|
367
|
-
|
|
368
|
-
|
|
369
|
-
invalid: Integer,
|
|
370
|
-
submitted: Integer
|
|
371
|
-
}
|
|
374
|
+
T::Array[
|
|
375
|
+
ContextDev::Models::BatchListResponse::Data::Format::TaggedSymbol
|
|
376
|
+
]
|
|
372
377
|
)
|
|
373
378
|
end
|
|
374
|
-
def
|
|
379
|
+
def self.values
|
|
375
380
|
end
|
|
376
381
|
end
|
|
377
382
|
|
|
378
|
-
# How pages
|
|
383
|
+
# How pages were selected. Matches `input.mode` on the submit request.
|
|
379
384
|
module Mode
|
|
380
385
|
extend ContextDev::Internal::Type::Enum
|
|
381
386
|
|
|
@@ -420,8 +425,9 @@ module ContextDev
|
|
|
420
425
|
sig { returns(Integer) }
|
|
421
426
|
attr_accessor :failed
|
|
422
427
|
|
|
423
|
-
#
|
|
424
|
-
#
|
|
428
|
+
# Reserved pages not yet attempted. A cancelled batch keeps reporting the URLs it
|
|
429
|
+
# never reached; a crawl whose `input.reserved_is_ceiling` is true reports 0 once
|
|
430
|
+
# final, because its unspent budget was never real pages.
|
|
425
431
|
sig { returns(Integer) }
|
|
426
432
|
attr_accessor :pending
|
|
427
433
|
|
|
@@ -429,7 +435,7 @@ module ContextDev
|
|
|
429
435
|
sig { returns(Integer) }
|
|
430
436
|
attr_accessor :succeeded
|
|
431
437
|
|
|
432
|
-
#
|
|
438
|
+
# Pages attempted so far. Use `status` to check completion.
|
|
433
439
|
sig do
|
|
434
440
|
params(
|
|
435
441
|
failed: Integer,
|
|
@@ -440,8 +446,9 @@ module ContextDev
|
|
|
440
446
|
def self.new(
|
|
441
447
|
# Pages that could not be scraped.
|
|
442
448
|
failed:,
|
|
443
|
-
#
|
|
444
|
-
#
|
|
449
|
+
# Reserved pages not yet attempted. A cancelled batch keeps reporting the URLs it
|
|
450
|
+
# never reached; a crawl whose `input.reserved_is_ceiling` is true reports 0 once
|
|
451
|
+
# final, because its unspent budget was never real pages.
|
|
445
452
|
pending:,
|
|
446
453
|
# Pages scraped successfully.
|
|
447
454
|
succeeded:
|
|
@@ -480,8 +487,8 @@ module ContextDev
|
|
|
480
487
|
end
|
|
481
488
|
attr_accessor :files
|
|
482
489
|
|
|
483
|
-
# Download links available
|
|
484
|
-
# serves the same records as paginated JSON.
|
|
490
|
+
# Download links, available once the batch reaches a final status and null before
|
|
491
|
+
# then. GET /batch/{batch_id}/results serves the same records as paginated JSON.
|
|
485
492
|
sig do
|
|
486
493
|
params(
|
|
487
494
|
expires_at: String,
|
|
@@ -659,38 +666,6 @@ module ContextDev
|
|
|
659
666
|
def to_hash
|
|
660
667
|
end
|
|
661
668
|
end
|
|
662
|
-
|
|
663
|
-
# Output format.
|
|
664
|
-
module Type
|
|
665
|
-
extend ContextDev::Internal::Type::Enum
|
|
666
|
-
|
|
667
|
-
TaggedSymbol =
|
|
668
|
-
T.type_alias do
|
|
669
|
-
T.all(Symbol, ContextDev::Models::BatchListResponse::Data::Type)
|
|
670
|
-
end
|
|
671
|
-
OrSymbol = T.type_alias { T.any(Symbol, String) }
|
|
672
|
-
|
|
673
|
-
MARKDOWN =
|
|
674
|
-
T.let(
|
|
675
|
-
:markdown,
|
|
676
|
-
ContextDev::Models::BatchListResponse::Data::Type::TaggedSymbol
|
|
677
|
-
)
|
|
678
|
-
HTML =
|
|
679
|
-
T.let(
|
|
680
|
-
:html,
|
|
681
|
-
ContextDev::Models::BatchListResponse::Data::Type::TaggedSymbol
|
|
682
|
-
)
|
|
683
|
-
|
|
684
|
-
sig do
|
|
685
|
-
override.returns(
|
|
686
|
-
T::Array[
|
|
687
|
-
ContextDev::Models::BatchListResponse::Data::Type::TaggedSymbol
|
|
688
|
-
]
|
|
689
|
-
)
|
|
690
|
-
end
|
|
691
|
-
def self.values
|
|
692
|
-
end
|
|
693
|
-
end
|
|
694
669
|
end
|
|
695
670
|
|
|
696
671
|
class KeyMetadata < ContextDev::Internal::Type::BaseModel
|