tangwang / SearchEngine

Commit c86c8237c01f306edbc5fad41dc397ddd47c9012

Authored by tangwang
1 parent 167a0cb2

支持聚合。过滤项补充了逻辑，但是有问题

Showing 16 changed files with 1976 additions and 35 deletions   Show diff stats
Inline Side-by-side
api/models.py
  Show/Hide comments   View file @c86c823
... ... @@ -13,6 +13,10 @@ class SearchRequest(BaseModel):
13 13 from_: int = Field(0, ge=0, alias="from", description="Offset for pagination")
14 14 filters: Optional[Dict[str, Any]] = Field(None, description="Additional filters")
15 15 min_score: Optional[float] = Field(None, description="Minimum score threshold")
  16 + # 新增字段
  17 + aggregations: Optional[Dict[str, Any]] = Field(None, description="Aggregation specifications")
  18 + sort_by: Optional[str] = Field(None, description="Sort field name")
  19 + sort_order: Optional[str] = Field("desc", description="Sort order: 'asc' or 'desc'")
16 20  
17 21  
18 22 class ImageSearchRequest(BaseModel):
... ...
api/routes/search.py
  Show/Hide comments   View file @c86c823
... ... @@ -68,7 +68,10 @@ async def search(request: SearchRequest, http_request: Request):
68 68 from_=request.from_,
69 69 filters=request.filters,
70 70 min_score=request.min_score,
71   - context=context
  71 + context=context,
  72 + aggregations=request.aggregations,
  73 + sort_by=request.sort_by,
  74 + sort_order=request.sort_order
72 75 )
73 76  
74 77 # Include performance summary in response
... ...
config/schema/customer1_config.yaml
  Show/Hide comments   View file @c86c823
... ... @@ -115,6 +115,21 @@ fields:
115 115 index: true
116 116 store: false
117 117  
  118 + - name: "supplierName_keyword"
  119 + type: "KEYWORD"
  120 + source_table: "extension"
  121 + source_column: "supplierName"
  122 + index: true
  123 + store: false
  124 +
  125 + # Price Fields
  126 + - name: "price"
  127 + type: "DOUBLE"
  128 + source_table: "extension"
  129 + source_column: "price"
  130 + index: true
  131 + store: true
  132 +
118 133 # Text Embedding Fields
119 134 - name: "name_embedding"
120 135 type: "TEXT_EMBEDDING"
... ...
debug_sort_query.py 0 → 100644
  Show/Hide comments   View file @c86c823
... ... @@ -0,0 +1,89 @@
  1 +#!/usr/bin/env python3
  2 +"""
  3 +Debug script to check the generated ES query for sorting
  4 +"""
  5 +
  6 +import requests
  7 +import json
  8 +
  9 +def test_simple_sort():
  10 + """Test simple sort functionality via API"""
  11 +
  12 + print("Testing simple sort via API...")
  13 +
  14 + # Test without sort first
  15 + request_no_sort = {
  16 + "query": "芭比",
  17 + "size": 1
  18 + }
  19 +
  20 + print("\n1. Search without sort:")
  21 + try:
  22 + response = requests.post("http://120.76.41.98:6002/search/", json=request_no_sort)
  23 + print(f"Status: {response.status_code}")
  24 + if response.ok:
  25 + data = response.json()
  26 + print(f"Results: {data.get('total', 0)} found in {data.get('took_ms', 0)}ms")
  27 + else:
  28 + print(f"Error: {response.text}")
  29 + except Exception as e:
  30 + print(f"Exception: {e}")
  31 +
  32 + # Test with sort
  33 + request_with_sort = {
  34 + "query": "芭比",
  35 + "size": 1,
  36 + "sort_by": "create_time",
  37 + "sort_order": "desc"
  38 + }
  39 +
  40 + print("\n2. Search with sort:")
  41 + print(f"Request: {json.dumps(request_with_sort, ensure_ascii=False, indent=2)}")
  42 +
  43 + try:
  44 + response = requests.post("http://120.76.41.98:6002/search/", json=request_with_sort)
  45 + print(f"Status: {response.status_code}")
  46 + if response.ok:
  47 + data = response.json()
  48 + print(f"Results: {data.get('total', 0)} found in {data.get('took_ms', 0)}ms")
  49 +
  50 + if 'hits' in data and data['hits']:
  51 + hit = data['hits'][0]
  52 + source = hit.get('_source', {})
  53 + print(f"Sample result: {source.get('name', 'N/A')}")
  54 + print(f"Create time: {source.get('create_time', 'N/A')}")
  55 + else:
  56 + print(f"Error: {response.text}")
  57 + except Exception as e:
  58 + print(f"Exception: {e}")
  59 +
  60 + # Test with different sort field
  61 + request_price_sort = {
  62 + "query": "芭比",
  63 + "size": 1,
  64 + "sort_by": "price",
  65 + "sort_order": "asc"
  66 + }
  67 +
  68 + print("\n3. Search with price sort:")
  69 + print(f"Request: {json.dumps(request_price_sort, ensure_ascii=False, indent=2)}")
  70 +
  71 + try:
  72 + response = requests.post("http://120.76.41.98:6002/search/", json=request_price_sort)
  73 + print(f"Status: {response.status_code}")
  74 + if response.ok:
  75 + data = response.json()
  76 + print(f"Results: {data.get('total', 0)} found in {data.get('took_ms', 0)}ms")
  77 +
  78 + if 'hits' in data and data['hits']:
  79 + hit = data['hits'][0]
  80 + source = hit.get('_source', {})
  81 + print(f"Sample result: {source.get('name', 'N/A')}")
  82 + print(f"Price: {source.get('price', 'N/A')}")
  83 + else:
  84 + print(f"Error: {response.text}")
  85 + except Exception as e:
  86 + print(f"Exception: {e}")
  87 +
  88 +if __name__ == "__main__":
  89 + test_simple_sort()
0 90 \ No newline at end of file
... ...
frontend/index.html
  Show/Hide comments   View file @c86c823
... ... @@ -21,14 +21,18 @@
21 21 </div>
22 22  
23 23 <div class="search-options">
24   - <label><input type="checkbox" id="enableTranslation" checked> 启用翻译</label>
25   - <label><input type="checkbox" id="enableEmbedding" checked> 启用语义搜索</label>
26   - <label><input type="checkbox" id="enableRerank" checked> 启用自定义排序</label>
27 24 <select id="resultSize">
28 25 <option value="10">10条结果</option>
29 26 <option value="20">20条结果</option>
30 27 <option value="50">50条结果</option>
31 28 </select>
  29 + <select id="sortBy">
  30 + <option value="">默认排序</option>
  31 + <option value="create_time:desc">上架时间（新到旧）</option>
  32 + <option value="create_time:asc">上架时间（旧到新）</option>
  33 + <option value="price:asc">价格（低到高）</option>
  34 + <option value="price:desc">价格（高到低）</option>
  35 + </select>
32 36 </div>
33 37  
34 38 <div class="search-examples">
... ... @@ -45,9 +49,19 @@
45 49 <p>搜索中...</p>
46 50 </div>
47 51  
48   - <div id="results" class="results-section"></div>
  52 + <div class="content-wrapper">
  53 + <div id="aggregationPanel" class="aggregation-panel" style="display: none;">
  54 + <h3>筛选条件</h3>
  55 + <div id="activeFilters" class="active-filters"></div>
  56 + <div id="aggregationResults" class="aggregation-results"></div>
  57 + </div>
  58 +
  59 + <div class="main-content">
  60 + <div id="results" class="results-section"></div>
49 61  
50   - <div id="queryInfo" class="query-info"></div>
  62 + <div id="queryInfo" class="query-info"></div>
  63 + </div>
  64 + </div>
51 65 </div>
52 66  
53 67 <footer>
... ...
frontend/static/css/style.css
  Show/Hide comments   View file @c86c823
... ... @@ -280,3 +280,153 @@ footer {
280 280 font-size: 24px;
281 281 margin-bottom: 10px;
282 282 }
  283 +
  284 +/* Layout for aggregation and main content */
  285 +.content-wrapper {
  286 + display: flex;
  287 + gap: 20px;
  288 + align-items: flex-start;
  289 +}
  290 +
  291 +/* Aggregation Panel */
  292 +.aggregation-panel {
  293 + background: white;
  294 + border-radius: 15px;
  295 + padding: 20px;
  296 + box-shadow: 0 10px 30px rgba(0,0,0,0.1);
  297 + width: 300px;
  298 + flex-shrink: 0;
  299 +}
  300 +
  301 +.aggregation-panel h3 {
  302 + color: #333;
  303 + margin-bottom: 20px;
  304 + font-size: 1.3em;
  305 + border-bottom: 2px solid #667eea;
  306 + padding-bottom: 10px;
  307 +}
  308 +
  309 +/* Active Filters */
  310 +.active-filters-list {
  311 + margin-bottom: 20px;
  312 + display: flex;
  313 + flex-wrap: wrap;
  314 + gap: 8px;
  315 + align-items: center;
  316 +}
  317 +
  318 +.active-filter-tag {
  319 + background: #667eea;
  320 + color: white;
  321 + padding: 4px 8px;
  322 + border-radius: 15px;
  323 + font-size: 12px;
  324 + display: flex;
  325 + align-items: center;
  326 + gap: 5px;
  327 +}
  328 +
  329 +.remove-filter {
  330 + background: none;
  331 + border: none;
  332 + color: white;
  333 + cursor: pointer;
  334 + font-size: 14px;
  335 + font-weight: bold;
  336 + padding: 0;
  337 + width: 16px;
  338 + height: 16px;
  339 + border-radius: 50%;
  340 + display: flex;
  341 + align-items: center;
  342 + justify-content: center;
  343 +}
  344 +
  345 +.remove-filter:hover {
  346 + background: rgba(255,255,255,0.2);
  347 +}
  348 +
  349 +.clear-filters {
  350 + background: #ff4444;
  351 + color: white;
  352 + border: none;
  353 + padding: 4px 12px;
  354 + border-radius: 15px;
  355 + font-size: 12px;
  356 + cursor: pointer;
  357 + transition: background 0.3s;
  358 +}
  359 +
  360 +.clear-filters:hover {
  361 + background: #cc0000;
  362 +}
  363 +
  364 +/* Aggregation Groups */
  365 +.aggregation-group {
  366 + margin-bottom: 25px;
  367 +}
  368 +
  369 +.aggregation-group h4 {
  370 + color: #555;
  371 + margin-bottom: 10px;
  372 + font-size: 1.1em;
  373 + font-weight: 600;
  374 +}
  375 +
  376 +.aggregation-items {
  377 + display: flex;
  378 + flex-direction: column;
  379 + gap: 8px;
  380 +}
  381 +
  382 +.aggregation-item {
  383 + display: flex;
  384 + align-items: center;
  385 + gap: 8px;
  386 + cursor: pointer;
  387 + padding: 5px;
  388 + border-radius: 5px;
  389 + transition: background-color 0.2s;
  390 +}
  391 +
  392 +.aggregation-item:hover {
  393 + background-color: #f5f5f5;
  394 +}
  395 +
  396 +.aggregation-item input[type="checkbox"] {
  397 + margin: 0;
  398 +}
  399 +
  400 +.aggregation-item span {
  401 + flex: 1;
  402 + font-size: 14px;
  403 + color: #333;
  404 +}
  405 +
  406 +.aggregation-item .count {
  407 + color: #888;
  408 + font-size: 12px;
  409 + font-weight: normal;
  410 +}
  411 +
  412 +/* Main content area */
  413 +.main-content {
  414 + flex: 1;
  415 + min-width: 0; /* Allow content to shrink */
  416 +}
  417 +
  418 +/* Responsive design */
  419 +@media (max-width: 768px) {
  420 + .content-wrapper {
  421 + flex-direction: column;
  422 + }
  423 +
  424 + .aggregation-panel {
  425 + width: 100%;
  426 + order: 2; /* Show below results on mobile */
  427 + }
  428 +
  429 + .main-content {
  430 + order: 1;
  431 + }
  432 +}
... ...
frontend/static/js/app.js
  Show/Hide comments   View file @c86c823
... ... @@ -19,6 +19,9 @@ function setQuery(query) {
19 19 performSearch();
20 20 }
21 21  
  22 +// 全局变量存储当前的过滤条件
  23 +let currentFilters = {};
  24 +
22 25 // Perform search
23 26 async function performSearch() {
24 27 const query = document.getElementById('searchInput').value.trim();
... ... @@ -28,16 +31,57 @@ async function performSearch() {
28 31 return;
29 32 }
30 33  
31   - // Get options (temporarily disable translation and embedding due to GPU issues)
  34 + // Get options
32 35 const size = parseInt(document.getElementById('resultSize').value);
33   - const enableTranslation = false; // Disabled temporarily
34   - const enableEmbedding = false; // Disabled temporarily
35   - const enableRerank = document.getElementById('enableRerank').checked;
  36 + const sortByValue = document.getElementById('sortBy').value;
  37 +
  38 + // Parse sort option
  39 + let sort_by = null;
  40 + let sort_order = 'desc';
  41 + if (sortByValue) {
  42 + const [field, order] = sortByValue.split(':');
  43 + sort_by = field;
  44 + sort_order = order;
  45 + }
  46 +
  47 + // Define aggregations for faceted search
  48 + const aggregations = {
  49 + "category_stats": {
  50 + "terms": {
  51 + "field": "categoryName_keyword",
  52 + "size": 10
  53 + }
  54 + },
  55 + "brand_stats": {
  56 + "terms": {
  57 + "field": "brandName_keyword",
  58 + "size": 10
  59 + }
  60 + },
  61 + "supplier_stats": {
  62 + "terms": {
  63 + "field": "supplierName_keyword",
  64 + "size": 10
  65 + }
  66 + },
  67 + "price_ranges": {
  68 + "range": {
  69 + "field": "price",
  70 + "ranges": [
  71 + {"key": "0-50", "to": 50},
  72 + {"key": "50-100", "from": 50, "to": 100},
  73 + {"key": "100-200", "from": 100, "to": 200},
  74 + {"key": "200+", "from": 200}
  75 + ]
  76 + }
  77 + }
  78 + };
36 79  
37 80 // Show loading
38 81 document.getElementById('loading').style.display = 'block';
39 82 document.getElementById('results').innerHTML = '';
40 83 document.getElementById('queryInfo').innerHTML = '';
  84 + document.getElementById('aggregationResults').innerHTML = '';
41 85  
42 86 try {
43 87 const response = await fetch(`${API_BASE_URL}/search/`, {
... ... @@ -48,9 +92,10 @@ async function performSearch() {
48 92 body: JSON.stringify({
49 93 query: query,
50 94 size: size,
51   - enable_translation: enableTranslation,
52   - enable_embedding: enableEmbedding,
53   - enable_rerank: enableRerank
  95 + filters: Object.keys(currentFilters).length > 0 ? currentFilters : null,
  96 + aggregations: aggregations,
  97 + sort_by: sort_by,
  98 + sort_order: sort_order
54 99 })
55 100 });
56 101  
... ... @@ -61,6 +106,8 @@ async function performSearch() {
61 106 const data = await response.json();
62 107 displayResults(data);
63 108 displayQueryInfo(data.query_info);
  109 + displayAggregations(data.aggregations);
  110 + displayActiveFilters();
64 111  
65 112 } catch (error) {
66 113 console.error('Search error:', error);
... ... @@ -119,6 +166,7 @@ function displayResults(data) {
119 166 </div>
120 167  
121 168 <div class="result-meta">
  169 + ${source.price ? `<span>💰 ¥${escapeHtml(source.price)}</span>` : ''}
122 170 ${source.categoryName ? `<span>📁 ${escapeHtml(source.categoryName)}</span>` : ''}
123 171 ${source.brandName ? `<span>🏷️ ${escapeHtml(source.brandName)}</span>` : ''}
124 172 ${source.supplierName ? `<span>🏭 ${escapeHtml(source.supplierName)}</span>` : ''}
... ... @@ -227,6 +275,236 @@ function getLanguageName(code) {
227 275 return names[code] || code;
228 276 }
229 277  
  278 +// Display aggregations
  279 +function displayAggregations(aggregations) {
  280 + if (!aggregations || Object.keys(aggregations).length === 0) {
  281 + document.getElementById('aggregationPanel').style.display = 'none';
  282 + return;
  283 + }
  284 +
  285 + document.getElementById('aggregationPanel').style.display = 'block';
  286 + const aggregationResultsDiv = document.getElementById('aggregationResults');
  287 +
  288 + let html = '';
  289 +
  290 + // Category aggregation
  291 + if (aggregations.category_stats && aggregations.category_stats.buckets) {
  292 + html += `
  293 + <div class="aggregation-group">
  294 + <h4>商品分类</h4>
  295 + <div class="aggregation-items">
  296 + `;
  297 +
  298 + aggregations.category_stats.buckets.forEach(bucket => {
  299 + const key = bucket.key;
  300 + const count = bucket.doc_count;
  301 + const isChecked = currentFilters.categoryName_keyword && currentFilters.categoryName_keyword.includes(key);
  302 +
  303 + html += `
  304 + <label class="aggregation-item">
  305 + <input type="checkbox"
  306 + ${isChecked ? 'checked' : ''}
  307 + onchange="toggleFilter('categoryName_keyword', '${escapeHtml(key)}', this.checked)">
  308 + <span>${escapeHtml(key)}</span>
  309 + <span class="count">(${count})</span>
  310 + </label>
  311 + `;
  312 + });
  313 +
  314 + html += '</div></div>';
  315 + }
  316 +
  317 + // Brand aggregation
  318 + if (aggregations.brand_stats && aggregations.brand_stats.buckets) {
  319 + html += `
  320 + <div class="aggregation-group">
  321 + <h4>品牌</h4>
  322 + <div class="aggregation-items">
  323 + `;
  324 +
  325 + aggregations.brand_stats.buckets.forEach(bucket => {
  326 + const key = bucket.key;
  327 + const count = bucket.doc_count;
  328 + const isChecked = currentFilters.brandName_keyword && currentFilters.brandName_keyword.includes(key);
  329 +
  330 + html += `
  331 + <label class="aggregation-item">
  332 + <input type="checkbox"
  333 + ${isChecked ? 'checked' : ''}
  334 + onchange="toggleFilter('brandName_keyword', '${escapeHtml(key)}', this.checked)">
  335 + <span>${escapeHtml(key)}</span>
  336 + <span class="count">(${count})</span>
  337 + </label>
  338 + `;
  339 + });
  340 +
  341 + html += '</div></div>';
  342 + }
  343 +
  344 + // Supplier aggregation
  345 + if (aggregations.supplier_stats && aggregations.supplier_stats.buckets) {
  346 + html += `
  347 + <div class="aggregation-group">
  348 + <h4>供应商</h4>
  349 + <div class="aggregation-items">
  350 + `;
  351 +
  352 + aggregations.supplier_stats.buckets.slice(0, 5).forEach(bucket => {
  353 + const key = bucket.key;
  354 + const count = bucket.doc_count;
  355 + const isChecked = currentFilters.supplierName_keyword && currentFilters.supplierName_keyword.includes(key);
  356 +
  357 + html += `
  358 + <label class="aggregation-item">
  359 + <input type="checkbox"
  360 + ${isChecked ? 'checked' : ''}
  361 + onchange="toggleFilter('supplierName_keyword', '${escapeHtml(key)}', this.checked)">
  362 + <span>${escapeHtml(key)}</span>
  363 + <span class="count">(${count})</span>
  364 + </label>
  365 + `;
  366 + });
  367 +
  368 + html += '</div></div>';
  369 + }
  370 +
  371 + // Price range aggregation
  372 + if (aggregations.price_ranges && aggregations.price_ranges.buckets) {
  373 + html += `
  374 + <div class="aggregation-group">
  375 + <h4>价格区间</h4>
  376 + <div class="aggregation-items">
  377 + `;
  378 +
  379 + aggregations.price_ranges.buckets.forEach(bucket => {
  380 + const key = bucket.key;
  381 + const count = bucket.doc_count;
  382 + const isChecked = currentFilters.price_ranges && currentFilters.price_ranges.includes(key);
  383 +
  384 + const priceLabel = {
  385 + '0-50': '¥0-50',
  386 + '50-100': '¥50-100',
  387 + '100-200': '¥100-200',
  388 + '200+': '¥200+'
  389 + };
  390 +
  391 + html += `
  392 + <label class="aggregation-item">
  393 + <input type="checkbox"
  394 + ${isChecked ? 'checked' : ''}
  395 + onchange="togglePriceFilter('${escapeHtml(key)}', this.checked)">
  396 + <span>${priceLabel[key] || key}</span>
  397 + <span class="count">(${count})</span>
  398 + </label>
  399 + `;
  400 + });
  401 +
  402 + html += '</div></div>';
  403 + }
  404 +
  405 + aggregationResultsDiv.innerHTML = html;
  406 +}
  407 +
  408 +// Display active filters
  409 +function displayActiveFilters() {
  410 + const activeFiltersDiv = document.getElementById('activeFilters');
  411 +
  412 + if (Object.keys(currentFilters).length === 0) {
  413 + activeFiltersDiv.innerHTML = '';
  414 + return;
  415 + }
  416 +
  417 + let html = '<div class="active-filters-list">';
  418 +
  419 + Object.entries(currentFilters).forEach(([field, values]) => {
  420 + if (Array.isArray(values)) {
  421 + values.forEach(value => {
  422 + let displayValue = value;
  423 + if (field === 'price_ranges') {
  424 + const priceLabel = {
  425 + '0-50': '¥0-50',
  426 + '50-100': '¥50-100',
  427 + '100-200': '¥100-200',
  428 + '200+': '¥200+'
  429 + };
  430 + displayValue = priceLabel[value] || value;
  431 + }
  432 +
  433 + html += `
  434 + <span class="active-filter-tag">
  435 + ${escapeHtml(displayValue)}
  436 + <button onclick="removeFilter('${field}', '${escapeHtml(value)}')" class="remove-filter">×</button>
  437 + </span>
  438 + `;
  439 + });
  440 + }
  441 + });
  442 +
  443 + html += `<button onclick="clearAllFilters()" class="clear-filters">清除所有</button></div>`;
  444 + activeFiltersDiv.innerHTML = html;
  445 +}
  446 +
  447 +// Toggle filter
  448 +function toggleFilter(field, value, checked) {
  449 + if (checked) {
  450 + if (!currentFilters[field]) {
  451 + currentFilters[field] = [];
  452 + }
  453 + if (!currentFilters[field].includes(value)) {
  454 + currentFilters[field].push(value);
  455 + }
  456 + } else {
  457 + if (currentFilters[field]) {
  458 + const index = currentFilters[field].indexOf(value);
  459 + if (index > -1) {
  460 + currentFilters[field].splice(index, 1);
  461 + }
  462 + if (currentFilters[field].length === 0) {
  463 + delete currentFilters[field];
  464 + }
  465 + }
  466 + }
  467 +
  468 + // Re-run search with new filters
  469 + performSearch();
  470 +}
  471 +
  472 +// Toggle price filter
  473 +function togglePriceFilter(value, checked) {
  474 + if (checked) {
  475 + if (!currentFilters.price_ranges) {
  476 + currentFilters.price_ranges = [];
  477 + }
  478 + if (!currentFilters.price_ranges.includes(value)) {
  479 + currentFilters.price_ranges.push(value);
  480 + }
  481 + } else {
  482 + if (currentFilters.price_ranges) {
  483 + const index = currentFilters.price_ranges.indexOf(value);
  484 + if (index > -1) {
  485 + currentFilters.price_ranges.splice(index, 1);
  486 + }
  487 + if (currentFilters.price_ranges.length === 0) {
  488 + delete currentFilters.price_ranges;
  489 + }
  490 + }
  491 + }
  492 +
  493 + // Re-run search with new filters
  494 + performSearch();
  495 +}
  496 +
  497 +// Remove single filter
  498 +function removeFilter(field, value) {
  499 + toggleFilter(field, value, false);
  500 +}
  501 +
  502 +// Clear all filters
  503 +function clearAllFilters() {
  504 + currentFilters = {};
  505 + performSearch();
  506 +}
  507 +
230 508 // Initialize page
231 509 document.addEventListener('DOMContentLoaded', function() {
232 510 console.log('SearchEngine Frontend loaded');
... ...
search/es_query_builder.py
  Show/Hide comments   View file @c86c823
... ... @@ -202,7 +202,36 @@ class ESQueryBuilder:
202 202 filter_clauses = []
203 203  
204 204 for field, value in filters.items():
205   - if isinstance(value, dict):
  205 + if field == 'price_ranges':
  206 + # Handle price range filters
  207 + if isinstance(value, list):
  208 + price_ranges = []
  209 + for price_range in value:
  210 + if price_range == '0-50':
  211 + price_ranges.append({"lt": 50})
  212 + elif price_range == '50-100':
  213 + price_ranges.append({"gte": 50, "lt": 100})
  214 + elif price_range == '100-200':
  215 + price_ranges.append({"gte": 100, "lt": 200})
  216 + elif price_range == '200+':
  217 + price_ranges.append({"gte": 200})
  218 +
  219 + if price_ranges:
  220 + if len(price_ranges) == 1:
  221 + filter_clauses.append({
  222 + "range": {
  223 + "price": price_ranges[0]
  224 + }
  225 + })
  226 + else:
  227 + # Multiple price ranges - use bool should clause
  228 + range_clauses = [{"range": {"price": pr}} for pr in price_ranges]
  229 + filter_clauses.append({
  230 + "bool": {
  231 + "should": range_clauses
  232 + }
  233 + })
  234 + elif isinstance(value, dict):
206 235 # Range query
207 236 if "gte" in value or "lte" in value or "gt" in value or "lt" in value:
208 237 filter_clauses.append({
... ... @@ -266,6 +295,65 @@ class ESQueryBuilder:
266 295  
267 296 return es_query
268 297  
  298 + def add_dynamic_aggregations(
  299 + self,
  300 + es_query: Dict[str, Any],
  301 + aggregations: Dict[str, Any]
  302 + ) -> Dict[str, Any]:
  303 + """
  304 + Add dynamic aggregations based on request parameters.
  305 +
  306 + Args:
  307 + es_query: Existing ES query
  308 + aggregations: Aggregation specifications
  309 +
  310 + Returns:
  311 + Modified ES query
  312 + """
  313 + if "aggs" not in es_query:
  314 + es_query["aggs"] = {}
  315 +
  316 + for agg_name, agg_spec in aggregations.items():
  317 + es_query["aggs"][agg_name] = agg_spec
  318 +
  319 + return es_query
  320 +
  321 + def add_sorting(
  322 + self,
  323 + es_query: Dict[str, Any],
  324 + sort_by: str,
  325 + sort_order: str = "desc"
  326 + ) -> Dict[str, Any]:
  327 + """
  328 + Add sorting to ES query.
  329 +
  330 + Args:
  331 + es_query: Existing ES query
  332 + sort_by: Field name for sorting
  333 + sort_order: Sort order: 'asc' or 'desc'
  334 +
  335 + Returns:
  336 + Modified ES query
  337 + """
  338 + if not sort_by:
  339 + return es_query
  340 +
  341 + if not sort_order:
  342 + sort_order = "desc"
  343 +
  344 + if "sort" not in es_query:
  345 + es_query["sort"] = []
  346 +
  347 + # Add the specified sort
  348 + sort_field = {
  349 + sort_by: {
  350 + "order": sort_order.lower()
  351 + }
  352 + }
  353 + es_query["sort"].append(sort_field)
  354 +
  355 + return es_query
  356 +
269 357 def add_aggregations(
270 358 self,
271 359 es_query: Dict[str, Any],
... ...
search/multilang_query_builder.py
  Show/Hide comments   View file @c86c823
... ... @@ -319,7 +319,11 @@ class MultiLanguageQueryBuilder(ESQueryBuilder):
319 319 if hasattr(node, 'operator'):
320 320 # QueryNode object
321 321 operator = node.operator
322   - terms = node.terms
  322 + terms = node.terms if hasattr(node, 'terms') else None
  323 +
  324 + # For TERM nodes, check if there's a value
  325 + if operator == 'TERM' and hasattr(node, 'value') and node.value:
  326 + terms = node.value
323 327 elif isinstance(node, tuple) and len(node) > 0:
324 328 # Tuple format from boolean parser
325 329 if hasattr(node[0], 'operator'):
... ... @@ -353,9 +357,7 @@ class MultiLanguageQueryBuilder(ESQueryBuilder):
353 357 else:
354 358 return {"match_all": {}}
355 359  
356   - print(f"[MultiLangQueryBuilder] Building boolean query for operator: {operator}")
357   - print(f"[MultiLangQueryBuilder] Terms: {terms}")
358   -
  360 +
359 361 if operator == 'TERM':
360 362 # Leaf node - handle field:query format
361 363 if isinstance(terms, str) and ':' in terms:
... ... @@ -365,31 +367,58 @@ class MultiLanguageQueryBuilder(ESQueryBuilder):
365 367 field: value
366 368 }
367 369 }
  370 + elif isinstance(terms, str):
  371 + # Simple text term - create match query
  372 + return {
  373 + "multi_match": {
  374 + "query": terms,
  375 + "fields": self.match_fields,
  376 + "type": "best_fields",
  377 + "operator": "AND"
  378 + }
  379 + }
368 380 else:
369   - return {"match_all": {}}
  381 + # Invalid TERM node - return empty match
  382 + return {
  383 + "match_none": {}
  384 + }
370 385  
371 386 elif operator == 'OR':
372 387 # Any term must match
373 388 should_clauses = []
374   - for term in terms:
375   - should_clauses.append(self._build_boolean_query_from_tuple(term))
376   - return {
377   - "bool": {
378   - "should": should_clauses,
379   - "minimum_should_match": 1
  389 + if terms:
  390 + for term in terms:
  391 + clause = self._build_boolean_query_from_tuple(term)
  392 + if clause and clause.get("match_none") is None:
  393 + should_clauses.append(clause)
  394 +
  395 + if should_clauses:
  396 + return {
  397 + "bool": {
  398 + "should": should_clauses,
  399 + "minimum_should_match": 1
  400 + }
380 401 }
381   - }
  402 + else:
  403 + return {"match_none": {}}
382 404  
383 405 elif operator == 'AND':
384 406 # All terms must match
385 407 must_clauses = []
386   - for term in terms:
387   - must_clauses.append(self._build_boolean_query_from_tuple(term))
388   - return {
389   - "bool": {
390   - "must": must_clauses
  408 + if terms:
  409 + for term in terms:
  410 + clause = self._build_boolean_query_from_tuple(term)
  411 + if clause and clause.get("match_none") is None:
  412 + must_clauses.append(clause)
  413 +
  414 + if must_clauses:
  415 + return {
  416 + "bool": {
  417 + "must": must_clauses
  418 + }
391 419 }
392   - }
  420 + else:
  421 + return {"match_none": {}}
393 422  
394 423 elif operator == 'ANDNOT':
395 424 # First term must match, second must not
... ...
search/searcher.py
  Show/Hide comments   View file @c86c823
... ... @@ -103,7 +103,10 @@ class Searcher:
103 103 from_: int = 0,
104 104 filters: Optional[Dict[str, Any]] = None,
105 105 min_score: Optional[float] = None,
106   - context: Optional[RequestContext] = None
  106 + context: Optional[RequestContext] = None,
  107 + aggregations: Optional[Dict[str, Any]] = None,
  108 + sort_by: Optional[str] = None,
  109 + sort_order: Optional[str] = "desc"
107 110 ) -> SearchResult:
108 111 """
109 112 Execute search query.
... ... @@ -115,6 +118,9 @@ class Searcher:
115 118 filters: Additional filters (field: value pairs)
116 119 min_score: Minimum score threshold
117 120 context: Request context for tracking (created if not provided)
  121 + aggregations: Aggregation specifications for faceted search
  122 + sort_by: Field name for sorting
  123 + sort_order: Sort order: 'asc' or 'desc'
118 124  
119 125 Returns:
120 126 SearchResult object
... ... @@ -146,7 +152,10 @@ class Searcher:
146 152 'enable_translation': enable_translation,
147 153 'enable_embedding': enable_embedding,
148 154 'enable_rerank': enable_rerank,
149   - 'min_score': min_score
  155 + 'min_score': min_score,
  156 + 'aggregations': aggregations,
  157 + 'sort_by': sort_by,
  158 + 'sort_order': sort_order
150 159 }
151 160  
152 161 context.metadata['feature_flags'] = {
... ... @@ -247,11 +256,19 @@ class Searcher:
247 256 )
248 257  
249 258 # Add aggregations for faceted search
250   - if filters:
  259 + if aggregations:
  260 + # Use dynamic aggregations from request
  261 + es_query = self.query_builder.add_dynamic_aggregations(es_query, aggregations)
  262 + elif filters:
  263 + # Fallback to filter-based aggregations
251 264 agg_fields = [f"{k}_keyword" for k in filters.keys() if f"{k}_keyword" in [f.name for f in self.config.fields]]
252 265 if agg_fields:
253 266 es_query = self.query_builder.add_aggregations(es_query, agg_fields)
254 267  
  268 + # Add sorting if specified
  269 + if sort_by:
  270 + es_query = self.query_builder.add_sorting(es_query, sort_by, sort_order)
  271 +
255 272 # Extract size and from from body for ES client parameters
256 273 body_for_es = {k: v for k, v in es_query.items() if k not in ['size', 'from']}
257 274  
... ...
simple_server.py 0 → 100644
  Show/Hide comments   View file @c86c823
... ... @@ -0,0 +1,340 @@
  1 +#!/usr/bin/env python3
  2 +"""
  3 +Simple API server for testing aggregation functionality without external dependencies.
  4 +"""
  5 +
  6 +import json
  7 +import time
  8 +import random
  9 +from http.server import HTTPServer, BaseHTTPRequestHandler
  10 +from urllib.parse import urlparse, parse_qs
  11 +import threading
  12 +
  13 +class SearchAPIHandler(BaseHTTPRequestHandler):
  14 + """Simple API handler for search requests."""
  15 +
  16 + def do_OPTIONS(self):
  17 + """Handle CORS preflight requests."""
  18 + self.send_response(200)
  19 + self.send_header('Access-Control-Allow-Origin', '*')
  20 + self.send_header('Access-Control-Allow-Methods', 'GET, POST, OPTIONS')
  21 + self.send_header('Access-Control-Allow-Headers', 'Content-Type')
  22 + self.end_headers()
  23 +
  24 + def do_POST(self):
  25 + """Handle POST requests."""
  26 + if self.path == '/':
  27 + self.handle_search()
  28 + elif self.path == '/search/':
  29 + self.handle_search()
  30 + else:
  31 + self.send_response(404)
  32 + self.end_headers()
  33 +
  34 + def handle_search(self):
  35 + """Handle search requests with aggregations."""
  36 + try:
  37 + # Read request body
  38 + content_length = int(self.headers['Content-Length'])
  39 + post_data = self.rfile.read(content_length)
  40 + request_data = json.loads(post_data.decode('utf-8'))
  41 +
  42 + query = request_data.get('query', '')
  43 + size = request_data.get('size', 10)
  44 + sort_by = request_data.get('sort_by', 'relevance')
  45 + aggregations = request_data.get('aggregations', {})
  46 + filters = request_data.get('filters', {})
  47 +
  48 + print(f"Search request: query='{query}', size={size}, sort_by={sort_by}")
  49 + print(f"Aggregations: {list(aggregations.keys()) if aggregations else 'None'}")
  50 + print(f"Filters: {filters if filters else 'None'}")
  51 +
  52 + # Simulate processing time
  53 + time.sleep(0.1)
  54 +
  55 + # Generate mock search results
  56 + results = self.generate_mock_results(query, size, sort_by, filters)
  57 +
  58 + # Generate mock aggregations
  59 + aggregation_results = self.generate_mock_aggregations(aggregations, filters)
  60 +
  61 + # Build response
  62 + response = {
  63 + "hits": results,
  64 + "total": len(results) + random.randint(10, 100),
  65 + "max_score": round(random.uniform(1.5, 3.5), 3),
  66 + "took_ms": random.randint(15, 45),
  67 + "aggregations": aggregation_results,
  68 + "query_info": {
  69 + "original_query": query,
  70 + "rewritten_query": query,
  71 + "detected_language": "zh" if any('\u4e00' <= char <= '\u9fff' for char in query) else "en",
  72 + "domain": "default",
  73 + "translations": {},
  74 + "has_vector": False
  75 + }
  76 + }
  77 +
  78 + # Send response
  79 + self.send_response(200)
  80 + self.send_header('Content-Type', 'application/json')
  81 + self.send_header('Access-Control-Allow-Origin', '*')
  82 + self.end_headers()
  83 +
  84 + response_json = json.dumps(response, ensure_ascii=False, indent=2)
  85 + self.wfile.write(response_json.encode('utf-8'))
  86 +
  87 + print(f"Response sent with {len(results)} results and {len(aggregation_results)} aggregations")
  88 +
  89 + except Exception as e:
  90 + print(f"Error handling request: {e}")
  91 + self.send_response(500)
  92 + self.send_header('Content-Type', 'application/json')
  93 + self.send_header('Access-Control-Allow-Origin', '*')
  94 + self.end_headers()
  95 +
  96 + error_response = {
  97 + "error": str(e),
  98 + "detail": "Internal server error"
  99 + }
  100 +
  101 + self.wfile.write(json.dumps(error_response).encode('utf-8'))
  102 +
  103 + def generate_mock_results(self, query, size, sort_by, filters):
  104 + """Generate mock search results."""
  105 +
  106 + # Sample product data
  107 + sample_products = [
  108 + {
  109 + "skuId": 1001,
  110 + "name": "芭比娃娃梦幻套装",
  111 + "enSpuName": "Barbie Dream House Playset",
  112 + "ruSkuName": "Кукла Барби Мечтательный домик",
  113 + "categoryName": "芭比",
  114 + "brandName": "美泰",
  115 + "supplierName": "义乌玩具厂",
  116 + "price": 89.99,
  117 + "imageUrl": "https://picsum.photos/seed/barbie1/200/200.jpg",
  118 + "create_time": "2024-01-15T10:30:00Z",
  119 + "days_since_last_update": 45
  120 + },
  121 + {
  122 + "skuId": 1002,
  123 + "name": "芭比娃娃时尚系列",
  124 + "enSpuName": "Barbie Fashion Doll Collection",
  125 + "ruSkuName": "Кукла Барби Модная коллекция",
  126 + "categoryName": "芭比",
  127 + "brandName": "美泰",
  128 + "supplierName": "汕头玩具公司",
  129 + "price": 45.50,
  130 + "imageUrl": "https://picsum.photos/seed/barbie2/200/200.jpg",
  131 + "create_time": "2024-02-20T14:15:00Z",
  132 + "days_since_last_update": 30
  133 + },
  134 + {
  135 + "skuId": 1003,
  136 + "name": "儿童积木套装",
  137 + "enSpuName": "Kids Building Blocks Set",
  138 + "ruSkuName": "Детский строительный набор",
  139 + "categoryName": "积木",
  140 + "brandName": "乐高",
  141 + "supplierName": "深圳塑胶制品厂",
  142 + "price": 158.00,
  143 + "imageUrl": "https://picsum.photos/seed/blocks1/200/200.jpg",
  144 + "create_time": "2024-01-10T09:20:00Z",
  145 + "days_since_last_update": 60
  146 + },
  147 + {
  148 + "skuId": 1004,
  149 + "name": "消防车玩具模型",
  150 + "enSpuName": "Fire Truck Toy Model",
  151 + "ruSkuName": "Модель пожарной машины",
  152 + "categoryName": "小汽车",
  153 + "brandName": "多美卡",
  154 + "supplierName": "东莞玩具制造厂",
  155 + "price": 78.50,
  156 + "imageUrl": "https://picsum.photos/seed/firetruck1/200/200.jpg",
  157 + "create_time": "2024-03-05T16:45:00Z",
  158 + "days_since_last_update": 15
  159 + },
  160 + {
  161 + "skuId": 1005,
  162 + "name": "婴儿毛绒玩具",
  163 + "enSpuName": "Baby Plush Toy",
  164 + "ruSkuName": "Детская плюшевая игрушка",
  165 + "categoryName": "婴儿娃娃",
  166 + "brandName": "迪士尼",
  167 + "supplierName": "上海礼品公司",
  168 + "price": 32.00,
  169 + "imageUrl": "https://picsum.photos/seed/plush1/200/200.jpg",
  170 + "create_time": "2024-02-14T11:30:00Z",
  171 + "days_since_last_update": 25
  172 + }
  173 + ]
  174 +
  175 + # Apply filters if any
  176 + if filters:
  177 + filtered_products = []
  178 + for product in sample_products:
  179 + include = True
  180 +
  181 + # Check category filter
  182 + if 'category_name' in filters:
  183 + if product['categoryName'] not in filters['category_name']:
  184 + include = False
  185 +
  186 + # Check brand filter
  187 + if 'brand_name' in filters:
  188 + if product['brandName'] not in filters['brand_name']:
  189 + include = False
  190 +
  191 + # Check price range filter
  192 + if 'price_ranges' in filters:
  193 + price = product['price']
  194 + in_range = False
  195 + for price_range in filters['price_ranges']:
  196 + if price_range == '0-50' and price <= 50:
  197 + in_range = True
  198 + elif price_range == '50-100' and 50 < price <= 100:
  199 + in_range = True
  200 + elif price_range == '100-200' and 100 < price <= 200:
  201 + in_range = True
  202 + elif price_range == '200+' and price > 200:
  203 + in_range = True
  204 + if not in_range:
  205 + include = False
  206 +
  207 + if include:
  208 + filtered_products.append(product)
  209 + sample_products = filtered_products
  210 +
  211 + # Apply sorting
  212 + if sort_by == 'price_asc':
  213 + sample_products.sort(key=lambda x: x.get('price', 0))
  214 + elif sort_by == 'price_desc':
  215 + sample_products.sort(key=lambda x: x.get('price', 0), reverse=True)
  216 + elif sort_by == 'time_desc':
  217 + sample_products.sort(key=lambda x: x.get('create_time', ''), reverse=True)
  218 +
  219 + # Convert to API response format
  220 + results = []
  221 + for i, product in enumerate(sample_products[:size]):
  222 + hit = {
  223 + "_id": str(product['skuId']),
  224 + "_score": round(random.uniform(1.5, 3.5), 3),
  225 + "_source": product
  226 + }
  227 + results.append(hit)
  228 +
  229 + return results
  230 +
  231 + def generate_mock_aggregations(self, aggregations, filters):
  232 + """Generate mock aggregation results."""
  233 + if not aggregations:
  234 + return {}
  235 +
  236 + result = {}
  237 +
  238 + for agg_name, agg_spec in aggregations.items():
  239 + agg_type = agg_spec.get('type', 'terms')
  240 +
  241 + if agg_type == 'terms':
  242 + # Generate mock terms aggregation
  243 + if agg_name == 'category_name':
  244 + buckets = [
  245 + {"key": "芭比", "doc_count": random.randint(15, 35)},
  246 + {"key": "儿童娃娃", "doc_count": random.randint(8, 20)},
  247 + {"key": "积木", "doc_count": random.randint(5, 15)},
  248 + {"key": "小汽车", "doc_count": random.randint(3, 12)},
  249 + {"key": "婴儿娃娃", "doc_count": random.randint(4, 10)},
  250 + {"key": "人物", "doc_count": random.randint(6, 18)}
  251 + ]
  252 + elif agg_name == 'brand_name':
  253 + buckets = [
  254 + {"key": "美泰", "doc_count": random.randint(20, 40)},
  255 + {"key": "乐高", "doc_count": random.randint(10, 25)},
  256 + {"key": "迪士尼", "doc_count": random.randint(8, 20)},
  257 + {"key": "多美卡", "doc_count": random.randint(5, 15)},
  258 + {"key": "孩之宝", "doc_count": random.randint(6, 18)},
  259 + {"key": "万代", "doc_count": random.randint(3, 10)}
  260 + ]
  261 + elif agg_name == 'material_type':
  262 + buckets = [
  263 + {"key": "塑料", "doc_count": random.randint(40, 80)},
  264 + {"key": "布绒", "doc_count": random.randint(8, 20)},
  265 + {"key": "金属", "doc_count": random.randint(5, 15)},
  266 + {"key": "木质", "doc_count": random.randint(3, 12)}
  267 + ]
  268 + else:
  269 + # Generic terms aggregation
  270 + buckets = [
  271 + {"key": f"选项{i+1}", "doc_count": random.randint(5, 25)}
  272 + for i in range(5)
  273 + ]
  274 +
  275 + result[agg_name] = {
  276 + "doc_count_error_upper_bound": 0,
  277 + "sum_other_doc_count": random.randint(10, 50),
  278 + "buckets": buckets
  279 + }
  280 +
  281 + elif agg_type == 'range':
  282 + # Generate mock range aggregation (usually for price)
  283 + if agg_name == 'price_ranges':
  284 + ranges = agg_spec.get('ranges', [])
  285 + buckets = []
  286 + for range_spec in ranges:
  287 + key = range_spec.get('key', 'unknown')
  288 + count = random.randint(5, 30)
  289 + bucket_data = {"key": key, "doc_count": count}
  290 +
  291 + # Add range bounds
  292 + if 'to' in range_spec:
  293 + bucket_data['to'] = range_spec['to']
  294 + if 'from' in range_spec:
  295 + bucket_data['from'] = range_spec['from']
  296 +
  297 + buckets.append(bucket_data)
  298 +
  299 + result[agg_name] = {"buckets": buckets}
  300 +
  301 + return result
  302 +
  303 + def log_message(self, format, *args):
  304 + """Override to reduce log noise."""
  305 + pass
  306 +
  307 +def run_server():
  308 + """Run the API server."""
  309 + server_address = ('', 6002)
  310 + httpd = HTTPServer(server_address, SearchAPIHandler)
  311 + print("🚀 Simple Search API Server started!")
  312 + print("📍 API: http://localhost:6002")
  313 + print("🔍 Search endpoint: http://localhost:6002/search/")
  314 + print("🌐 Frontend should connect to: http://localhost:6002")
  315 + print("⏹️ Press Ctrl+C to stop")
  316 +
  317 + try:
  318 + httpd.serve_forever()
  319 + except KeyboardInterrupt:
  320 + print("\n🛑 Server stopped")
  321 + httpd.server_close()
  322 +
  323 +def run_server():
  324 + """Run the API server - main entry point."""
  325 + server_address = ('', 6002)
  326 + httpd = HTTPServer(server_address, SearchAPIHandler)
  327 + print("🚀 Simple Search API Server started!")
  328 + print("📍 API: http://localhost:6002")
  329 + print("🔍 Search endpoint: http://localhost:6002/search/")
  330 + print("🌐 Frontend should connect to: http://localhost:6002")
  331 + print("⏹️ Press Ctrl+C to stop")
  332 +
  333 + try:
  334 + httpd.serve_forever()
  335 + except KeyboardInterrupt:
  336 + print("\n🛑 Server stopped")
  337 + httpd.server_close()
  338 +
  339 +if __name__ == '__main__':
  340 + run_server()
0 341 \ No newline at end of file
... ...
test_aggregation_api.py 0 → 100644
  Show/Hide comments   View file @c86c823
... ... @@ -0,0 +1,166 @@
  1 +#!/usr/bin/env python3
  2 +"""
  3 +Test script for aggregation functionality
  4 +"""
  5 +
  6 +import requests
  7 +import json
  8 +
  9 +API_BASE_URL = 'http://120.76.41.98:6002'
  10 +
  11 +def test_search_with_aggregations():
  12 + """Test search with aggregations"""
  13 +
  14 + # Test data
  15 + test_query = {
  16 + "query": "玩具",
  17 + "size": 5,
  18 + "aggregations": {
  19 + "category_stats": {
  20 + "terms": {
  21 + "field": "categoryName_keyword",
  22 + "size": 10
  23 + }
  24 + },
  25 + "brand_stats": {
  26 + "terms": {
  27 + "field": "brandName_keyword",
  28 + "size": 10
  29 + }
  30 + },
  31 + "price_ranges": {
  32 + "range": {
  33 + "field": "price",
  34 + "ranges": [
  35 + {"key": "0-50", "to": 50},
  36 + {"key": "50-100", "from": 50, "to": 100},
  37 + {"key": "100-200", "from": 100, "to": 200},
  38 + {"key": "200+", "from": 200}
  39 + ]
  40 + }
  41 + }
  42 + }
  43 + }
  44 +
  45 + print("Testing search with aggregations...")
  46 + print(f"Query: {json.dumps(test_query, indent=2, ensure_ascii=False)}")
  47 +
  48 + try:
  49 + response = requests.post(f"{API_BASE_URL}/search/",
  50 + json=test_query,
  51 + headers={'Content-Type': 'application/json'})
  52 +
  53 + print(f"Status Code: {response.status_code}")
  54 +
  55 + if response.ok:
  56 + data = response.json()
  57 + print(f"Found {data['total']} results in {data['took_ms']}ms")
  58 + print(f"Max Score: {data['max_score']}")
  59 +
  60 + # Print aggregations
  61 + if data.get('aggregations'):
  62 + print("\nAggregations:")
  63 + for agg_name, agg_result in data['aggregations'].items():
  64 + print(f"\n{agg_name}:")
  65 + if 'buckets' in agg_result:
  66 + for bucket in agg_result['buckets'][:5]: # Show first 5 buckets
  67 + print(f" - {bucket['key']}: {bucket['doc_count']}")
  68 +
  69 + # Print first few results
  70 + print(f"\nFirst 3 results:")
  71 + for i, hit in enumerate(data['hits'][:3]):
  72 + source = hit['_source']
  73 + print(f"\n{i+1}. {source.get('name', 'N/A')}")
  74 + print(f" Category: {source.get('categoryName', 'N/A')}")
  75 + print(f" Brand: {source.get('brandName', 'N/A')}")
  76 + print(f" Price: {source.get('price', 'N/A')}")
  77 + print(f" Score: {hit['_score']:.4f}")
  78 + else:
  79 + print(f"Error: {response.status_code}")
  80 + print(f"Response: {response.text}")
  81 +
  82 + except Exception as e:
  83 + print(f"Request failed: {e}")
  84 +
  85 +def test_search_with_filters():
  86 + """Test search with filters"""
  87 +
  88 + test_filters = {
  89 + "query": "玩具",
  90 + "size": 5,
  91 + "filters": {
  92 + "categoryName_keyword": ["玩具"],
  93 + "price_ranges": ["0-50", "50-100"]
  94 + }
  95 + }
  96 +
  97 + print("\n\nTesting search with filters...")
  98 + print(f"Query: {json.dumps(test_filters, indent=2, ensure_ascii=False)}")
  99 +
  100 + try:
  101 + response = requests.post(f"{API_BASE_URL}/search/",
  102 + json=test_filters,
  103 + headers={'Content-Type': 'application/json'})
  104 +
  105 + print(f"Status Code: {response.status_code}")
  106 +
  107 + if response.ok:
  108 + data = response.json()
  109 + print(f"Found {data['total']} results in {data['took_ms']}ms")
  110 +
  111 + print(f"\nFirst 3 results:")
  112 + for i, hit in enumerate(data['hits'][:3]):
  113 + source = hit['_source']
  114 + print(f"\n{i+1}. {source.get('name', 'N/A')}")
  115 + print(f" Category: {source.get('categoryName', 'N/A')}")
  116 + print(f" Brand: {source.get('brandName', 'N/A')}")
  117 + print(f" Price: {source.get('price', 'N/A')}")
  118 + print(f" Score: {hit['_score']:.4f}")
  119 + else:
  120 + print(f"Error: {response.status_code}")
  121 + print(f"Response: {response.text}")
  122 +
  123 + except Exception as e:
  124 + print(f"Request failed: {e}")
  125 +
  126 +def test_search_with_sorting():
  127 + """Test search with sorting"""
  128 +
  129 + test_sort = {
  130 + "query": "玩具",
  131 + "size": 5,
  132 + "sort_by": "price",
  133 + "sort_order": "asc"
  134 + }
  135 +
  136 + print("\n\nTesting search with sorting (price ascending)...")
  137 + print(f"Query: {json.dumps(test_sort, indent=2, ensure_ascii=False)}")
  138 +
  139 + try:
  140 + response = requests.post(f"{API_BASE_URL}/search/",
  141 + json=test_sort,
  142 + headers={'Content-Type': 'application/json'})
  143 +
  144 + print(f"Status Code: {response.status_code}")
  145 +
  146 + if response.ok:
  147 + data = response.json()
  148 + print(f"Found {data['total']} results in {data['took_ms']}ms")
  149 +
  150 + print(f"\nFirst 3 results (sorted by price):")
  151 + for i, hit in enumerate(data['hits'][:3]):
  152 + source = hit['_source']
  153 + print(f"\n{i+1}. {source.get('name', 'N/A')}")
  154 + print(f" Price: {source.get('price', 'N/A')}")
  155 + print(f" Score: {hit['_score']:.4f}")
  156 + else:
  157 + print(f"Error: {response.status_code}")
  158 + print(f"Response: {response.text}")
  159 +
  160 + except Exception as e:
  161 + print(f"Request failed: {e}")
  162 +
  163 +if __name__ == "__main__":
  164 + test_search_with_aggregations()
  165 + test_search_with_filters()
  166 + test_search_with_sorting()
0 167 \ No newline at end of file
... ...
test_aggregation_functionality.py 0 → 100644
  Show/Hide comments   View file @c86c823
... ... @@ -0,0 +1,236 @@
  1 +#!/usr/bin/env python3
  2 +"""
  3 +Simple test script to verify aggregation functionality without external dependencies.
  4 +"""
  5 +
  6 +import sys
  7 +import os
  8 +
  9 +# Add the project root to the Python path
  10 +sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
  11 +
  12 +def test_es_query_builder_aggregations():
  13 + """Test the ES query builder aggregation methods."""
  14 + print("Testing ES Query Builder Aggregation Methods...")
  15 +
  16 + # Import the query builder
  17 + try:
  18 + from search.es_query_builder import ESQueryBuilder
  19 + print("✓ ESQueryBuilder imported successfully")
  20 + except ImportError as e:
  21 + print(f"✗ Failed to import ESQueryBuilder: {e}")
  22 + return False
  23 +
  24 + # Create a query builder instance
  25 + builder = ESQueryBuilder(
  26 + index_name="test_index",
  27 + match_fields=["name", "description"]
  28 + )
  29 +
  30 + # Test basic aggregation
  31 + es_query = {"query": {"match_all": {}}}
  32 +
  33 + # Test add_dynamic_aggregations
  34 + aggregations = {
  35 + "category_name": {
  36 + "type": "terms",
  37 + "field": "categoryName_keyword",
  38 + "size": 10
  39 + },
  40 + "price_ranges": {
  41 + "type": "range",
  42 + "field": "price",
  43 + "ranges": [
  44 + {"key": "0-50", "to": 50},
  45 + {"key": "50-100", "from": 50, "to": 100}
  46 + ]
  47 + }
  48 + }
  49 +
  50 + result_query = builder.add_dynamic_aggregations(es_query, aggregations)
  51 +
  52 + if "aggs" in result_query:
  53 + print("✓ Aggregations added to query")
  54 +
  55 + # Check category aggregation
  56 + if "category_name" in result_query["aggs"]:
  57 + category_agg = result_query["aggs"]["category_name"]
  58 + if "terms" in category_agg and category_agg["terms"]["field"] == "categoryName_keyword":
  59 + print("✓ Category aggregation correctly configured")
  60 + else:
  61 + print("✗ Category aggregation incorrectly configured")
  62 + return False
  63 +
  64 + # Check price range aggregation
  65 + if "price_ranges" in result_query["aggs"]:
  66 + price_agg = result_query["aggs"]["price_ranges"]
  67 + if "range" in price_agg and price_agg["range"]["field"] == "price":
  68 + print("✓ Price range aggregation correctly configured")
  69 + else:
  70 + print("✗ Price range aggregation incorrectly configured")
  71 + return False
  72 + else:
  73 + print("✗ No aggregations added to query")
  74 + return False
  75 +
  76 + # Test sorting
  77 + result_query_asc = builder.add_sorting({}, "price_asc")
  78 + if "sort" in result_query_asc:
  79 + print("✓ Price ascending sort added")
  80 + else:
  81 + print("✗ Price ascending sort not added")
  82 + return False
  83 +
  84 + result_query_desc = builder.add_sorting({}, "price_desc")
  85 + if "sort" in result_query_desc:
  86 + print("✓ Price descending sort added")
  87 + else:
  88 + print("✗ Price descending sort not added")
  89 + return False
  90 +
  91 + result_query_time = builder.add_sorting({}, "time_desc")
  92 + if "sort" in result_query_time:
  93 + print("✓ Time descending sort added")
  94 + else:
  95 + print("✗ Time descending sort not added")
  96 + return False
  97 +
  98 + return True
  99 +
  100 +
  101 +def test_searcher_integration():
  102 + """Test searcher integration with new parameters."""
  103 + print("\nTesting Searcher Integration...")
  104 +
  105 + try:
  106 + from search.searcher import Searcher
  107 + print("✓ Searcher imported successfully")
  108 + except ImportError as e:
  109 + print(f"✗ Failed to import Searcher: {e}")
  110 + return False
  111 +
  112 + # We can't easily test the full searcher without ES, but we can check the method signature
  113 + import inspect
  114 + search_method = getattr(Searcher, 'search', None)
  115 +
  116 + if search_method:
  117 + sig = inspect.signature(search_method)
  118 + params = list(sig.parameters.keys())
  119 +
  120 + expected_params = ['query', 'size', 'from_', 'filters', 'min_score', 'aggregations', 'sort_by', 'context']
  121 + for param in expected_params:
  122 + if param in params:
  123 + print(f"✓ Parameter '{param}' found in search method")
  124 + else:
  125 + print(f"✗ Parameter '{param}' missing from search method")
  126 + return False
  127 + else:
  128 + print("✗ Search method not found in Searcher class")
  129 + return False
  130 +
  131 + return True
  132 +
  133 +
  134 +def test_api_route_integration():
  135 + """Test API route integration."""
  136 + print("\nTesting API Route Integration...")
  137 +
  138 + try:
  139 + from api.routes.search import router
  140 + print("✓ Search router imported successfully")
  141 + except ImportError as e:
  142 + print(f"✗ Failed to import search router: {e}")
  143 + return False
  144 +
  145 + # Check if the route exists
  146 + routes = [route.path for route in router.routes]
  147 + if "/" in routes:
  148 + print("✓ Main search route found")
  149 + else:
  150 + print("✗ Main search route not found")
  151 + return False
  152 +
  153 + return True
  154 +
  155 +
  156 +def test_configuration():
  157 + """Test configuration parsing."""
  158 + print("\nTesting Configuration...")
  159 +
  160 + try:
  161 + from config import CustomerConfig
  162 + print("✓ CustomerConfig imported successfully")
  163 + except ImportError as e:
  164 + print(f"✗ Failed to import CustomerConfig: {e}")
  165 + return False
  166 +
  167 + # Try to load the customer1 config
  168 + try:
  169 + config = CustomerConfig.load_from_file("config/schema/customer1_config.yaml")
  170 + print("✓ Customer1 configuration loaded successfully")
  171 +
  172 + # Check if price field is in the configuration
  173 + field_names = [field.name for field in config.fields]
  174 + if "price" in field_names:
  175 + print("✓ Price field found in configuration")
  176 + else:
  177 + print("✗ Price field not found in configuration")
  178 + return False
  179 +
  180 + # Check keyword fields for aggregations
  181 + if "categoryName_keyword" in field_names:
  182 + print("✓ Category keyword field found")
  183 + else:
  184 + print("✗ Category keyword field not found")
  185 + return False
  186 +
  187 + if "brandName_keyword" in field_names:
  188 + print("✓ Brand keyword field found")
  189 + else:
  190 + print("✗ Brand keyword field not found")
  191 + return False
  192 +
  193 + except Exception as e:
  194 + print(f"✗ Failed to load configuration: {e}")
  195 + return False
  196 +
  197 + return True
  198 +
  199 +
  200 +def main():
  201 + """Run all tests."""
  202 + print("=== Search Engine Aggregation Functionality Tests ===\n")
  203 +
  204 + tests = [
  205 + test_es_query_builder_aggregations,
  206 + test_searcher_integration,
  207 + test_api_route_integration,
  208 + test_configuration
  209 + ]
  210 +
  211 + passed = 0
  212 + total = len(tests)
  213 +
  214 + for test in tests:
  215 + try:
  216 + if test():
  217 + passed += 1
  218 + print(f"✓ {test.__name__} PASSED")
  219 + else:
  220 + print(f"✗ {test.__name__} FAILED")
  221 + except Exception as e:
  222 + print(f"✗ {test.__name__} ERROR: {e}")
  223 +
  224 + print(f"\n=== Test Results: {passed}/{total} tests passed ===")
  225 +
  226 + if passed == total:
  227 + print("🎉 All tests passed! Aggregation functionality is ready.")
  228 + return True
  229 + else:
  230 + print("❌ Some tests failed. Please check the implementation.")
  231 + return False
  232 +
  233 +
  234 +if __name__ == "__main__":
  235 + success = main()
  236 + sys.exit(0 if success else 1)
0 237 \ No newline at end of file
... ...
test_complete_search.py 0 → 100644
  Show/Hide comments   View file @c86c823
... ... @@ -0,0 +1,211 @@
  1 +#!/usr/bin/env python3
  2 +"""
  3 +Complete test script simulating frontend search interaction
  4 +"""
  5 +
  6 +import requests
  7 +import json
  8 +
  9 +API_BASE_URL = 'http://120.76.41.98:6002'
  10 +
  11 +def test_complete_search_workflow():
  12 + """Test complete search workflow similar to frontend"""
  13 +
  14 + print("=" * 60)
  15 + print("完整搜索流程测试")
  16 + print("=" * 60)
  17 +
  18 + # Step 1: Initial search with aggregations
  19 + print("\n1️⃣ 初始搜索（带聚合功能）")
  20 + print("-" * 30)
  21 +
  22 + search_request = {
  23 + "query": "芭比娃娃",
  24 + "size": 10,
  25 + "aggregations": {
  26 + "category_stats": {
  27 + "terms": {
  28 + "field": "categoryName_keyword",
  29 + "size": 10
  30 + }
  31 + },
  32 + "brand_stats": {
  33 + "terms": {
  34 + "field": "brandName_keyword",
  35 + "size": 10
  36 + }
  37 + },
  38 + "price_ranges": {
  39 + "range": {
  40 + "field": "price",
  41 + "ranges": [
  42 + {"key": "0-50", "to": 50},
  43 + {"key": "50-100", "from": 50, "to": 100},
  44 + {"key": "100-200", "from": 100, "to": 200},
  45 + {"key": "200+", "from": 200}
  46 + ]
  47 + }
  48 + }
  49 + }
  50 + }
  51 +
  52 + try:
  53 + response = requests.post(f"{API_BASE_URL}/search/", json=search_request)
  54 +
  55 + if response.ok:
  56 + data = response.json()
  57 + print(f"✅ 找到 {data['total']} 个结果，耗时 {data['took_ms']}ms")
  58 +
  59 + # Show aggregations results
  60 + if data.get('aggregations'):
  61 + print("\n📊 聚合结果:")
  62 +
  63 + # Category aggregations
  64 + if 'category_stats' in data['aggregations']:
  65 + print(" 🏷️ 分类统计:")
  66 + for bucket in data['aggregations']['category_stats']['buckets'][:3]:
  67 + print(f" - {bucket['key']}: {bucket['doc_count']} 个商品")
  68 +
  69 + # Brand aggregations
  70 + if 'brand_stats' in data['aggregations']:
  71 + print(" 🏢 品牌统计:")
  72 + for bucket in data['aggregations']['brand_stats']['buckets'][:3]:
  73 + print(f" - {bucket['key']}: {bucket['doc_count']} 个商品")
  74 +
  75 + # Price ranges
  76 + if 'price_ranges' in data['aggregations']:
  77 + print(" 💰 价格分布:")
  78 + for bucket in data['aggregations']['price_ranges']['buckets']:
  79 + print(f" - {bucket['key']}: {bucket['doc_count']} 个商品")
  80 +
  81 + # Show sample results
  82 + print(f"\n🔍 前3个搜索结果:")
  83 + for i, hit in enumerate(data['hits'][:3]):
  84 + source = hit['_source']
  85 + price = source.get('price', 'N/A')
  86 + category = source.get('categoryName', 'N/A')
  87 + brand = source.get('brandName', 'N/A')
  88 + print(f" {i+1}. {source.get('name', 'N/A')}")
  89 + print(f" 💰 价格: {price}")
  90 + print(f" 📁 分类: {category}")
  91 + print(f" 🏷️ 品牌: {brand}")
  92 + print(f" ⭐ 评分: {hit['_score']:.3f}")
  93 + print()
  94 +
  95 + else:
  96 + print(f"❌ 搜索失败: {response.status_code}")
  97 + print(f"错误信息: {response.text}")
  98 +
  99 + except Exception as e:
  100 + print(f"❌ 请求异常: {e}")
  101 +
  102 + # Step 2: Search with filters
  103 + print("\n2️⃣ 带过滤条件的搜索")
  104 + print("-" * 30)
  105 +
  106 + filtered_search = {
  107 + "query": "芭比娃娃",
  108 + "size": 5,
  109 + "filters": {
  110 + "brandName_keyword": ["美泰"],
  111 + "price_ranges": ["50-100", "100-200"]
  112 + }
  113 + }
  114 +
  115 + try:
  116 + response = requests.post(f"{API_BASE_URL}/search/", json=filtered_search)
  117 +
  118 + if response.ok:
  119 + data = response.json()
  120 + print(f"✅ 过滤后找到 {data['total']} 个结果，耗时 {data['took_ms']}ms")
  121 + print(" 🎯 过滤条件: 品牌=美泰, 价格=¥50-200")
  122 +
  123 + print(f"\n💫 前3个过滤结果:")
  124 + for i, hit in enumerate(data['hits'][:3]):
  125 + source = hit['_source']
  126 + price = source.get('price', 'N/A')
  127 + category = source.get('categoryName', 'N/A')
  128 + brand = source.get('brandName', 'N/A')
  129 + print(f" {i+1}. {source.get('name', 'N/A')}")
  130 + print(f" 💰 ¥{price} | 📁 {category} | 🏷️ {brand}")
  131 + print(f" ⭐ 评分: {hit['_score']:.3f}")
  132 +
  133 + else:
  134 + print(f"❌ 过滤搜索失败: {response.status_code}")
  135 +
  136 + except Exception as e:
  137 + print(f"❌ 请求异常: {e}")
  138 +
  139 + # Step 3: Search with sorting
  140 + print("\n3️⃣ 排序搜索")
  141 + print("-" * 30)
  142 +
  143 + # Test price ascending
  144 + price_asc_search = {
  145 + "query": "芭比娃娃",
  146 + "size": 3,
  147 + "sort_by": "price",
  148 + "sort_order": "asc"
  149 + }
  150 +
  151 + try:
  152 + response = requests.post(f"{API_BASE_URL}/search/", json=price_asc_search)
  153 +
  154 + if response.ok:
  155 + data = response.json()
  156 + print(f"✅ 价格升序排序，找到 {data['total']} 个结果")
  157 + print(" 📈 排序方式: 价格从低到高")
  158 +
  159 + print(f"\n💵 价格排序结果:")
  160 + for i, hit in enumerate(data['hits']):
  161 + source = hit['_source']
  162 + price = source.get('price', 'N/A')
  163 + name = source.get('name', 'N/A')
  164 + print(f" {i+1}. ¥{price} - {name}")
  165 +
  166 + else:
  167 + print(f"❌ 排序搜索失败: {response.status_code}")
  168 +
  169 + except Exception as e:
  170 + print(f"❌ 请求异常: {e}")
  171 +
  172 + # Step 4: Test time sorting
  173 + print("\n4️⃣ 时间排序测试")
  174 + print("-" * 30)
  175 +
  176 + time_sort_search = {
  177 + "query": "芭比娃娃",
  178 + "size": 3,
  179 + "sort_by": "create_time",
  180 + "sort_order": "desc"
  181 + }
  182 +
  183 + try:
  184 + response = requests.post(f"{API_BASE_URL}/search/", json=time_sort_search)
  185 +
  186 + if response.ok:
  187 + data = response.json()
  188 + print(f"✅ 时间降序排序，找到 {data['total']} 个结果")
  189 + print(" 📅 排序方式: 上架时间从新到旧")
  190 +
  191 + print(f"\n🕐 时间排序结果:")
  192 + for i, hit in enumerate(data['hits']):
  193 + source = hit['_source']
  194 + create_time = source.get('create_time', 'N/A')
  195 + name = source.get('name', 'N/A')
  196 + print(f" {i+1}. {create_time} - {name}")
  197 +
  198 + else:
  199 + print(f"❌ 时间排序失败: {response.status_code}")
  200 +
  201 + except Exception as e:
  202 + print(f"❌ 请求异常: {e}")
  203 +
  204 + print("\n" + "=" * 60)
  205 + print("🎉 搜索功能测试完成！")
  206 + print("✨ 前端访问地址: http://localhost:8080")
  207 + print("🔧 后端API地址: http://120.76.41.98:6002")
  208 + print("=" * 60)
  209 +
  210 +if __name__ == "__main__":
  211 + test_complete_search_workflow()
0 212 \ No newline at end of file
... ...
test_minimal_sort.py 0 → 100644
  Show/Hide comments   View file @c86c823
... ... @@ -0,0 +1,45 @@
  1 +#!/usr/bin/env python3
  2 +"""
  3 +Minimal test to isolate sort issue
  4 +"""
  5 +
  6 +import requests
  7 +import json
  8 +
  9 +def test_minimal_sort():
  10 + """Test minimal sort case"""
  11 +
  12 + base_url = "http://120.76.41.98:6002"
  13 +
  14 + # Test 1: No sort parameters
  15 + print("Test 1: No sort parameters")
  16 + response = requests.post(f"{base_url}/search/", json={"query": "test", "size": 1})
  17 + print(f"Status: {response.status_code}")
  18 + print(f"Response: {response.text[:200]}...")
  19 +
  20 + # Test 2: Empty sort_by
  21 + print("\nTest 2: Empty sort_by")
  22 + response = requests.post(f"{base_url}/search/", json={"query": "test", "size": 1, "sort_by": ""})
  23 + print(f"Status: {response.status_code}")
  24 + print(f"Response: {response.text[:200]}...")
  25 +
  26 + # Test 3: sort_by only (no sort_order)
  27 + print("\nTest 3: sort_by only")
  28 + response = requests.post(f"{base_url}/search/", json={"query": "test", "size": 1, "sort_by": "create_time"})
  29 + print(f"Status: {response.status_code}")
  30 + print(f"Response: {response.text[:200]}...")
  31 +
  32 + # Test 4: sort_order only (no sort_by)
  33 + print("\nTest 4: sort_order only")
  34 + response = requests.post(f"{base_url}/search/", json={"query": "test", "size": 1, "sort_order": "desc"})
  35 + print(f"Status: {response.status_code}")
  36 + print(f"Response: {response.text[:200]}...")
  37 +
  38 + # Test 5: Both parameters with None values
  39 + print("\nTest 5: Both parameters with null values")
  40 + response = requests.post(f"{base_url}/search/", json={"query": "test", "size": 1, "sort_by": None, "sort_order": None})
  41 + print(f"Status: {response.status_code}")
  42 + print(f"Response: {response.text[:200]}...")
  43 +
  44 +if __name__ == "__main__":
  45 + test_minimal_sort()
0 46 \ No newline at end of file
... ...
tests/integration/test_aggregation_api.py 0 → 100644
  Show/Hide comments   View file @c86c823
... ... @@ -0,0 +1,256 @@
  1 +"""
  2 +Tests for aggregation API functionality.
  3 +"""
  4 +
  5 +import pytest
  6 +from fastapi.testclient import TestClient
  7 +from api.app import app
  8 +
  9 +client = TestClient(app)
  10 +
  11 +
  12 +@pytest.mark.integration
  13 +@pytest.mark.api
  14 +def test_search_with_aggregations():
  15 + """Test search with dynamic aggregations."""
  16 + request_data = {
  17 + "query": "芭比娃娃",
  18 + "size": 10,
  19 + "aggregations": {
  20 + "category_name": {
  21 + "type": "terms",
  22 + "field": "categoryName_keyword",
  23 + "size": 10
  24 + },
  25 + "brand_name": {
  26 + "type": "terms",
  27 + "field": "brandName_keyword",
  28 + "size": 10
  29 + },
  30 + "price_ranges": {
  31 + "type": "range",
  32 + "field": "price",
  33 + "ranges": [
  34 + {"key": "0-50", "to": 50},
  35 + {"key": "50-100", "from": 50, "to": 100},
  36 + {"key": "100-200", "from": 100, "to": 200},
  37 + {"key": "200+", "from": 200}
  38 + ]
  39 + }
  40 + }
  41 + }
  42 +
  43 + response = client.post("/search/", json=request_data)
  44 +
  45 + assert response.status_code == 200
  46 + data = response.json()
  47 +
  48 + # Check basic search response structure
  49 + assert "hits" in data
  50 + assert "total" in data
  51 + assert "aggregations" in data
  52 + assert "query_info" in data
  53 +
  54 + # Check aggregations structure
  55 + aggregations = data["aggregations"]
  56 +
  57 + # Should have category aggregations
  58 + if "category_name" in aggregations:
  59 + assert "buckets" in aggregations["category_name"]
  60 + assert isinstance(aggregations["category_name"]["buckets"], list)
  61 +
  62 + # Should have brand aggregations
  63 + if "brand_name" in aggregations:
  64 + assert "buckets" in aggregations["brand_name"]
  65 + assert isinstance(aggregations["brand_name"]["buckets"], list)
  66 +
  67 + # Should have price range aggregations
  68 + if "price_ranges" in aggregations:
  69 + assert "buckets" in aggregations["price_ranges"]
  70 + assert isinstance(aggregations["price_ranges"]["buckets"], list)
  71 +
  72 +
  73 +@pytest.mark.integration
  74 +@pytest.mark.api
  75 +def test_search_with_sorting():
  76 + """Test search with different sorting options."""
  77 +
  78 + # Test price ascending
  79 + request_data = {
  80 + "query": "玩具",
  81 + "size": 5,
  82 + "sort_by": "price_asc"
  83 + }
  84 +
  85 + response = client.post("/search/", json=request_data)
  86 + assert response.status_code == 200
  87 + data = response.json()
  88 +
  89 + if data["hits"] and len(data["hits"]) > 1:
  90 + # Check if results are sorted by price (ascending)
  91 + prices = []
  92 + for hit in data["hits"]:
  93 + if "_source" in hit and "price" in hit["_source"]:
  94 + prices.append(hit["_source"]["price"])
  95 +
  96 + if len(prices) > 1:
  97 + assert prices == sorted(prices), "Results should be sorted by price ascending"
  98 +
  99 + # Test price descending
  100 + request_data["sort_by"] = "price_desc"
  101 + response = client.post("/search/", json=request_data)
  102 + assert response.status_code == 200
  103 + data = response.json()
  104 +
  105 + if data["hits"] and len(data["hits"]) > 1:
  106 + prices = []
  107 + for hit in data["hits"]:
  108 + if "_source" in hit and "price" in hit["_source"]:
  109 + prices.append(hit["_source"]["price"])
  110 +
  111 + if len(prices) > 1:
  112 + assert prices == sorted(prices, reverse=True), "Results should be sorted by price descending"
  113 +
  114 + # Test time descending
  115 + request_data["sort_by"] = "time_desc"
  116 + response = client.post("/search/", json=request_data)
  117 + assert response.status_code == 200
  118 + data = response.json()
  119 +
  120 + if data["hits"] and len(data["hits"]) > 1:
  121 + times = []
  122 + for hit in data["hits"]:
  123 + if "_source" in hit and "create_time" in hit["_source"]:
  124 + times.append(hit["_source"]["create_time"])
  125 +
  126 + if len(times) > 1:
  127 + # Newer items should come first
  128 + assert times == sorted(times, reverse=True), "Results should be sorted by time descending"
  129 +
  130 +
  131 +@pytest.mark.integration
  132 +@pytest.mark.api
  133 +def test_search_with_filters_and_aggregations():
  134 + """Test search with filters and aggregations together."""
  135 + request_data = {
  136 + "query": "玩具",
  137 + "size": 10,
  138 + "filters": {
  139 + "category_name": ["芭比"]
  140 + },
  141 + "aggregations": {
  142 + "brand_name": {
  143 + "type": "terms",
  144 + "field": "brandName_keyword",
  145 + "size": 10
  146 + }
  147 + }
  148 + }
  149 +
  150 + response = client.post("/search/", json=request_data)
  151 + assert response.status_code == 200
  152 + data = response.json()
  153 +
  154 + # Check that results are filtered
  155 + assert "hits" in data
  156 + for hit in data["hits"]:
  157 + if "_source" in hit and "categoryName" in hit["_source"]:
  158 + assert "芭比" in hit["_source"]["categoryName"]
  159 +
  160 + # Check that aggregations are still present
  161 + assert "aggregations" in data
  162 +
  163 +
  164 +@pytest.mark.integration
  165 +@pytest.mark.api
  166 +def test_search_without_aggregations():
  167 + """Test search without aggregations (default behavior)."""
  168 + request_data = {
  169 + "query": "玩具",
  170 + "size": 10
  171 + }
  172 +
  173 + response = client.post("/search/", json=request_data)
  174 + assert response.status_code == 200
  175 + data = response.json()
  176 +
  177 + # Should still have basic response structure
  178 + assert "hits" in data
  179 + assert "total" in data
  180 + assert "query_info" in data
  181 +
  182 + # Aggregations might be empty or not present without explicit request
  183 + assert "aggregations" in data
  184 +
  185 +
  186 +@pytest.mark.integration
  187 +@pytest.mark.api
  188 +def test_aggregation_edge_cases():
  189 + """Test aggregation edge cases."""
  190 +
  191 + # Test with empty query
  192 + request_data = {
  193 + "query": "",
  194 + "size": 10,
  195 + "aggregations": {
  196 + "category_name": {
  197 + "type": "terms",
  198 + "field": "categoryName_keyword",
  199 + "size": 10
  200 + }
  201 + }
  202 + }
  203 +
  204 + response = client.post("/search/", json=request_data)
  205 + # Should handle empty query gracefully
  206 + assert response.status_code in [200, 422]
  207 +
  208 + # Test with invalid aggregation type
  209 + request_data = {
  210 + "query": "玩具",
  211 + "size": 10,
  212 + "aggregations": {
  213 + "invalid_agg": {
  214 + "type": "invalid_type",
  215 + "field": "categoryName_keyword",
  216 + "size": 10
  217 + }
  218 + }
  219 + }
  220 +
  221 + response = client.post("/search/", json=request_data)
  222 + # Should handle invalid aggregation type gracefully
  223 + assert response.status_code in [200, 422]
  224 +
  225 +
  226 +@pytest.mark.unit
  227 +def test_aggregation_spec_validation():
  228 + """Test aggregation specification validation."""
  229 + from api.models import AggregationSpec
  230 +
  231 + # Test valid aggregation spec
  232 + agg_spec = AggregationSpec(
  233 + field="categoryName_keyword",
  234 + type="terms",
  235 + size=10
  236 + )
  237 + assert agg_spec.field == "categoryName_keyword"
  238 + assert agg_spec.type == "terms"
  239 + assert agg_spec.size == 10
  240 +
  241 + # Test range aggregation spec
  242 + range_agg = AggregationSpec(
  243 + field="price",
  244 + type="range",
  245 + ranges=[
  246 + {"key": "0-50", "to": 50},
  247 + {"key": "50-100", "from": 50, "to": 100}
  248 + ]
  249 + )
  250 + assert range_agg.field == "price"
  251 + assert range_agg.type == "range"
  252 + assert len(range_agg.ranges) == 2
  253 +
  254 +
  255 +if __name__ == "__main__":
  256 + pytest.main([__file__])
0 257 \ No newline at end of file
... ...