crawlrs 0.2.0

crawlrs - Enterprise-grade web scraping and crawling platform built with Rust
Documentation
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
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
// Copyright (c) 2025-2026 Kirky.X🌠
// SPDX-License-Identifier: Apache-2.0

//! Task query handlers — GET-style task query operations.
//!
//! 从 `task_handler.rs` 拆分出的查询类处理器及其辅助函数。

#![allow(unused_variables)]

use crate::application::dto::task_query_request::{
    ScrapeResultInfoDto, TaskInfoDto, TaskQueryDataDto, TaskQueryRequestDto,
};
use crate::common::constants::crawl_task;
use crate::common::constants::server_config;
use crate::domain::models::TaskStatus;
use crate::domain::repositories::scrape_result_repository::ScrapeResultRepository;
use crate::domain::repositories::task_repository::{TaskQueryParams, TaskRepository};
use crate::infrastructure::repositories::scrape_result_repo_impl::ScrapeResultRepositoryImpl;
use crate::presentation::errors::CrawlRsError;
use crate::presentation::handlers::extract_task_ids;
use crate::presentation::handlers::response_builder::{json_rejection_error, ApiResponse};
use crate::presentation::middleware::auth_middleware::AuthState;
use anyhow;
use axum::{extract::Extension, Json};
use chrono::{TimeZone, Utc};
use sdforge::validator::Validate;
use std::sync::Arc;
use std::time::{Duration, Instant};
use tokio::time::sleep;

/// Poll task statuses until all complete or the timeout expires.
///
/// Uses adaptive polling: starts at `base_poll_interval_ms`, dynamically
/// adjusts between 500 ms – 2 000 ms based on completion rate, and caps
/// total iterations at `MAX_POLL_COUNT`.
///
/// # Arguments
///
/// * `task_repo` - Task repository for status polling.
/// * `task_ids` - IDs of tasks to wait for.
/// * `team_id` - Owning team (used for logging / authorization).
/// * `sync_wait_ms` - Maximum wait time in milliseconds.
/// * `base_poll_interval_ms` - Initial polling interval.
///
/// # Errors
///
/// Returns `CrawlRsError` if the repository cannot be reached.
pub async fn wait_for_tasks_completion(
    task_repo: &dyn TaskRepository,
    task_ids: &[crate::domain::id::Id],
    team_id: crate::domain::id::Id,
    sync_wait_ms: u32,
    base_poll_interval_ms: u64,
) -> Result<(), CrawlRsError> {
    let start_time = Instant::now();
    let timeout_duration = Duration::from_millis(sync_wait_ms as u64);
    let min_interval = 500u64;
    let max_interval = 2000u64;

    let mut current_interval = base_poll_interval_ms.clamp(min_interval, max_interval);
    let mut last_completion_rate = 0.0f64;
    let mut poll_count = 0u32;

    while start_time.elapsed() < timeout_duration {
        poll_count += 1;
        if poll_count_exceeded(poll_count, crawl_task::MAX_POLL_COUNT) {
            return Ok(());
        }

        let tasks = query_tasks_for_poll(task_repo, team_id, task_ids).await?;
        let completion_rate = calculate_completion_rate(&tasks, task_ids);

        if completion_rate >= 1.0 {
            return Ok(());
        }

        let new_interval = calculate_next_interval(
            completion_rate,
            last_completion_rate,
            current_interval,
            min_interval,
            max_interval,
        );
        current_interval = new_interval;
        last_completion_rate = completion_rate;

        let remaining_time = timeout_duration.saturating_sub(start_time.elapsed());
        let wait_duration = Duration::from_millis(current_interval).min(remaining_time);

        if !wait_duration.is_zero() {
            sleep(wait_duration).await;
        }
    }

    Ok(())
}

/// 检查是否达到最大轮询次数
#[inline]
pub(crate) fn poll_count_exceeded(count: u32, max_count: u32) -> bool {
    if count >= max_count {
        log::debug!("Reached max poll count ({}) for task completion", max_count);
        true
    } else {
        false
    }
}

/// 查询任务状态用于轮询
pub(crate) async fn query_tasks_for_poll(
    task_repo: &dyn TaskRepository,
    team_id: crate::domain::id::Id,
    task_ids: &[crate::domain::id::Id],
) -> Result<Vec<crate::domain::models::Task>, CrawlRsError> {
    let (tasks, _) = task_repo
        .query_tasks(TaskQueryParams {
            team_id,
            task_ids: Some(task_ids.to_vec()),
            limit: task_ids.len() as u32,
            ..Default::default()
        })
        .await?;
    Ok(tasks)
}

/// 计算任务完成率
#[inline]
pub(crate) fn calculate_completion_rate(
    tasks: &[crate::domain::models::Task],
    task_ids: &[crate::domain::id::Id],
) -> f64 {
    if task_ids.is_empty() {
        return 1.0;
    }

    let completed_count = tasks
        .iter()
        .filter(|task| {
            matches!(
                task.status,
                TaskStatus::Completed | TaskStatus::Failed | TaskStatus::Cancelled
            )
        })
        .count();

    completed_count as f64 / task_ids.len() as f64
}

/// 根据完成进度计算下一次轮询间隔
#[inline]
pub(crate) fn calculate_next_interval(
    completion_rate: f64,
    last_rate: f64,
    current_interval: u64,
    min_interval: u64,
    max_interval: u64,
) -> u64 {
    let progress = completion_rate - last_rate;
    let rate_based = min_interval + ((max_interval - min_interval) as f64 * completion_rate) as u64;

    match progress {
        p if p > 0.0 => ((current_interval as f64 * 1.2).max(rate_based as f64) as u64)
            .clamp(min_interval, max_interval),
        p if p < 0.0 => ((current_interval as f64 * 0.8).min(rate_based as f64) as u64)
            .clamp(min_interval, max_interval),
        _ => rate_based.clamp(min_interval, max_interval),
    }
}

/// 任务查询响应扩展数据
#[derive(Debug, Clone, serde::Serialize, serde::Deserialize)]
pub struct TaskQueryResponseMeta {
    /// 同步状态
    pub status: String,
    /// 消耗的积分
    pub credits_used: u32,
    /// 响应时间(毫秒)
    pub response_time_ms: u64,
}

/// Query tasks with pagination, filtering, and optional scrape-result enrichment.
///
/// # Arguments
///
/// * `auth_state` - Authenticated caller state.
/// * `task_repo` - Task repository for querying.
/// * `scrape_result_repo` - Scrape result repository for enrichment.
/// * `request` - Query parameters (pagination, filters, sync wait).
///
/// # Errors
///
/// Returns `CrawlRsError` on validation failure or repository error.
pub async fn query_tasks<T: TaskRepository>(
    Extension(auth_state): Extension<AuthState>,
    Extension(task_repo): Extension<Arc<T>>,
    Extension(scrape_result_repo): Extension<Arc<ScrapeResultRepositoryImpl>>,
    payload: Result<Json<TaskQueryRequestDto>, axum::extract::rejection::JsonRejection>,
) -> Result<Json<ApiResponse<TaskQueryDataDto>>, CrawlRsError> {
    // 提取器级拒绝(非法 JSON / 字段缺失)映射为统一包封(结构错误 422 / 语法错误 400)
    let request = extract_query_request(payload)?;
    let team_id = auth_state.team_id;
    let start_time = Instant::now();

    validate_request(&request)?;

    let (limit, offset, include_results, sync_wait_ms) = apply_defaults(&request);

    let task_types_clone = request.task_types.clone();
    let statuses_clone = request.statuses.clone();

    let (mut tasks, total) =
        execute_task_query(task_repo.as_ref(), team_id, &request, limit, offset).await?;

    if sync_wait_ms > 0 && !tasks.is_empty() {
        tasks = sync_wait_and_refresh(
            task_repo.as_ref(),
            team_id,
            &request,
            tasks,
            limit,
            offset,
            sync_wait_ms,
        )
        .await?;
    }

    // 获取抓取结果(如果需要)
    let task_id_to_result = if include_results && !tasks.is_empty() {
        fetch_scrape_results(scrape_result_repo.as_ref(), &tasks).await?
    } else {
        None
    };

    let task_infos = build_task_infos(&tasks, task_id_to_result.as_ref());

    let has_more = (offset + limit) < total as u32;

    Ok(Json(ApiResponse::success(TaskQueryDataDto {
        tasks: task_infos,
        total,
        has_more,
    })))
}

/// 提取请求体(自 [`query_tasks`] 提取):提取器级拒绝映射为统一包封
/// (结构错误 422 / 语法错误 400)。
fn extract_query_request(
    payload: Result<Json<TaskQueryRequestDto>, axum::extract::rejection::JsonRejection>,
) -> Result<TaskQueryRequestDto, CrawlRsError> {
    match payload {
        Ok(Json(request)) => Ok(request),
        Err(rej) => Err(json_rejection_error(rej)),
    }
}

/// 同步等待任务状态并在有进展时重查(自 [`query_tasks`] 提取)。
async fn sync_wait_and_refresh<T: TaskRepository>(
    task_repo: &T,
    team_id: crate::domain::id::Id,
    request: &TaskQueryRequestDto,
    mut tasks: Vec<crate::domain::models::Task>,
    limit: u32,
    offset: u32,
    sync_wait_ms: u32,
) -> Result<Vec<crate::domain::models::Task>, CrawlRsError> {
    let waited_time_ms = handle_sync_wait(task_repo, &tasks, team_id, sync_wait_ms).await?;

    // 重新查询任务状态
    if waited_time_ms > 0 {
        (tasks, _) = execute_task_query(task_repo, team_id, request, limit, offset).await?;
    }

    Ok(tasks)
}

/// 验证请求参数
pub(crate) fn validate_request(request: &TaskQueryRequestDto) -> Result<(), CrawlRsError> {
    if let Err(errors) = request.validate() {
        Err(CrawlRsError::Unprocessable(
            crate::presentation::handlers::response_builder::validation_error_message(&errors),
        ))
    } else {
        Ok(())
    }
}

/// 应用请求默认值并提取参数
pub(crate) fn apply_defaults(request: &TaskQueryRequestDto) -> (u32, u32, bool, u32) {
    (
        request
            .limit
            .unwrap_or(server_config::DEFAULT_PAGE_LIMIT)
            .min(server_config::MAX_PAGE_LIMIT),
        request.offset.unwrap_or(0),
        request.include_results.unwrap_or(false),
        request
            .sync_wait_ms
            .unwrap_or(crawl_task::DEFAULT_TIMEOUT_MS as u32),
    )
}

/// 执行任务查询
pub(crate) async fn execute_task_query<T: TaskRepository>(
    task_repo: &T,
    team_id: crate::domain::id::Id,
    request: &TaskQueryRequestDto,
    limit: u32,
    offset: u32,
) -> Result<(Vec<crate::domain::models::Task>, u64), CrawlRsError> {
    task_repo
        .query_tasks(TaskQueryParams {
            team_id,
            task_ids: request.task_ids.clone(),
            task_types: request.task_types.clone(),
            statuses: request.statuses.clone(),
            created_after: request.created_after.map(|dt| dt.with_timezone(&Utc)),
            created_before: request.created_before.map(|dt| dt.with_timezone(&Utc)),
            crawl_id: request.crawl_id,
            limit,
            offset,
            cursor: None,
            cursor_id: None,
        })
        .await
        .map_err(|e| CrawlRsError::from(anyhow::anyhow!("Query failed: {:?}", e)))
}

/// 处理同步等待模式
pub(crate) async fn handle_sync_wait<T: TaskRepository>(
    task_repo: &T,
    tasks: &[crate::domain::models::Task],
    team_id: crate::domain::id::Id,
    sync_wait_ms: u32,
) -> Result<u64, CrawlRsError> {
    let task_ids = extract_task_ids(tasks);
    let wait_start = Instant::now();

    wait_for_tasks_completion(
        task_repo,
        &task_ids,
        team_id,
        sync_wait_ms,
        crawl_task::BASE_POLL_INTERVAL_MS,
    )
    .await?;

    Ok(wait_start.elapsed().as_millis() as u64)
}

/// 同步等待结果
pub struct SyncWaitResult {
    /// 实际等待时间(毫秒)
    pub waited_time_ms: u64,
    /// 是否超时
    pub is_timeout: bool,
}

/// Orchestrate synchronous wait for a set of tasks and return the aggregate status.
///
/// This is the public entry-point used by handlers. When `sync_wait_ms` is
/// 0 or `task_ids` is empty the function returns immediately.
///
/// # Arguments
///
/// * `task_repo` - Task repository for polling.
/// * `task_ids` - IDs of tasks to monitor.
/// * `team_id` - Owning team.
/// * `sync_wait_ms` - Maximum wait time in milliseconds (0 = no wait).
///
/// # Errors
///
/// Returns `CrawlRsError` if the wait or repository call fails.
pub async fn handle_sync_wait_and_get_status(
    task_repo: &dyn TaskRepository,
    task_ids: &[crate::domain::id::Id],
    team_id: crate::domain::id::Id,
    sync_wait_ms: u32,
) -> Result<SyncWaitResult, CrawlRsError> {
    if sync_wait_ms == 0 || task_ids.is_empty() {
        return Ok(SyncWaitResult {
            waited_time_ms: 0,
            is_timeout: false,
        });
    }

    let wait_start = Instant::now();

    match wait_for_tasks_completion(
        task_repo,
        task_ids,
        team_id,
        sync_wait_ms,
        crawl_task::BASE_POLL_INTERVAL_MS,
    )
    .await
    {
        Ok(_) => {
            let waited_time_ms = wait_start.elapsed().as_millis() as u64;
            Ok(SyncWaitResult {
                waited_time_ms,
                is_timeout: waited_time_ms >= sync_wait_ms as u64,
            })
        }
        Err(e) => {
            log::error!("Failed to wait for task completion: {:?}", e);
            // 即使等待失败,也返回已创建的任务信息
            let waited_time_ms = wait_start.elapsed().as_millis() as u64;
            Ok(SyncWaitResult {
                waited_time_ms,
                is_timeout: waited_time_ms >= sync_wait_ms as u64,
            })
        }
    }
}

/// 获取抓取结果
pub(crate) async fn fetch_scrape_results(
    scrape_result_repo: &ScrapeResultRepositoryImpl,
    tasks: &[crate::domain::models::Task],
) -> Result<
    Option<std::collections::HashMap<crate::domain::id::Id, crate::domain::models::ScrapeResult>>,
    CrawlRsError,
> {
    let task_ids = extract_task_ids(tasks);
    let results = scrape_result_repo.find_by_task_ids(&task_ids).await?;

    let mut map = std::collections::HashMap::with_capacity(results.len());
    for result in results {
        map.insert(result.task_id, result);
    }
    Ok(Some(map))
}

/// 构建任务信息列表
pub(crate) fn build_task_infos(
    tasks: &[crate::domain::models::Task],
    results_map: Option<
        &std::collections::HashMap<crate::domain::id::Id, crate::domain::models::ScrapeResult>,
    >,
) -> Vec<TaskInfoDto> {
    tasks
        .iter()
        .map(|task| {
            let result = results_map
                .and_then(|m| m.get(&task.id))
                .map(build_scrape_result_json);
            TaskInfoDto {
                id: task.id,
                task_type: task.task_type,
                status: task.status,
                priority: task.priority,
                url: task.url.clone(),
                attempt_count: task.attempt_count,
                max_retries: task.max_retries,
                created_at: chrono::FixedOffset::east_opt(0)
                    .unwrap()
                    .from_utc_datetime(&task.created_at.naive_utc()),
                started_at: task.started_at.as_ref().map(|dt| {
                    chrono::FixedOffset::east_opt(0)
                        .unwrap()
                        .from_utc_datetime(&dt.naive_utc())
                }),
                completed_at: task.completed_at.as_ref().map(|dt| {
                    chrono::FixedOffset::east_opt(0)
                        .unwrap()
                        .from_utc_datetime(&dt.naive_utc())
                }),
                crawl_id: task.crawl_id,
                result,
            }
        })
        .collect()
}

/// 构建抓取结果信息
pub(crate) fn build_scrape_result_json(
    scrape_result: &crate::domain::models::ScrapeResult,
) -> ScrapeResultInfoDto {
    let escaped_content = html_escape::encode_text(&scrape_result.content);
    ScrapeResultInfoDto {
        id: scrape_result.id,
        status_code: scrape_result.status_code as u16,
        content: escaped_content.to_string(),
        metadata: Some(scrape_result.meta_data.clone()),
    }
}