update search
This commit is contained in:
Ross
+147
-107
@@ -249,11 +249,33 @@ def match_author(authors: List[Dict[str, Any]], q: str) -> bool:
|
||||
return False
|
||||
|
||||
|
||||
def run_search(root: str, qkey: str, qval: str, mode: str = 'exact', targets: List[str] = None) -> List[Dict[str, Any]]:
|
||||
def run_search(root: str, qkey: str, qval: str, mode: str = 'exact', targets: List[str] = None, or_queries: List[Dict[str, Any]] = None) -> List[Dict[str, Any]]:
|
||||
out = []
|
||||
|
||||
# Helper to test if a string/list/dict matches under the chosen mode
|
||||
def value_matches(query: str, target_val: Any) -> bool:
|
||||
# Normalize queries list
|
||||
if not or_queries:
|
||||
or_queries = [{
|
||||
'qkey': qkey,
|
||||
'qval': qval,
|
||||
'mode': mode,
|
||||
'targets': targets
|
||||
}]
|
||||
|
||||
normalized_specs = []
|
||||
for spec in or_queries:
|
||||
qk = spec.get('qkey') or 'global'
|
||||
qv = spec.get('qval') or ''
|
||||
m = spec.get('mode') or 'exact'
|
||||
t = spec.get('targets')
|
||||
normalized_specs.append({
|
||||
'qkey': qk,
|
||||
'qval': qv,
|
||||
'mode': m,
|
||||
'targets': t
|
||||
})
|
||||
|
||||
# Helper to test if a string/list/dict matches under a specific mode
|
||||
def value_matches(query: str, target_val: Any, mode_val: str) -> bool:
|
||||
if target_val is None:
|
||||
return False
|
||||
|
||||
@@ -261,15 +283,15 @@ def run_search(root: str, qkey: str, qval: str, mode: str = 'exact', targets: Li
|
||||
for item in target_val:
|
||||
if isinstance(item, dict):
|
||||
for k, v in item.items():
|
||||
if value_matches(query, v):
|
||||
if value_matches(query, v, mode_val):
|
||||
return True
|
||||
else:
|
||||
if value_matches(query, item):
|
||||
if value_matches(query, item, mode_val):
|
||||
return True
|
||||
return False
|
||||
elif isinstance(target_val, dict):
|
||||
for k, v in target_val.items():
|
||||
if value_matches(query, v):
|
||||
if value_matches(query, v, mode_val):
|
||||
return True
|
||||
return False
|
||||
|
||||
@@ -277,9 +299,9 @@ def run_search(root: str, qkey: str, qval: str, mode: str = 'exact', targets: Li
|
||||
if not s_val:
|
||||
return False
|
||||
|
||||
if mode == 'stemming':
|
||||
if mode_val == 'stemming':
|
||||
return match_stemming(query, s_val)
|
||||
elif mode == 'fuzzy':
|
||||
elif mode_val == 'fuzzy':
|
||||
return match_fuzzy(query, s_val)
|
||||
else:
|
||||
# Exact substring or wildcard match
|
||||
@@ -303,108 +325,126 @@ def run_search(root: str, qkey: str, qval: str, mode: str = 'exact', targets: Li
|
||||
reasons = []
|
||||
snippet = ""
|
||||
|
||||
# Normalise query key. If none or global/all/empty, search all
|
||||
k_lower = (qkey or '').strip().lower()
|
||||
if not k_lower or k_lower in ('global', 'all', 'any'):
|
||||
# Determine which targets to test
|
||||
if targets:
|
||||
target_set = {t.lower() for t in targets}
|
||||
else:
|
||||
target_set = {'title', 'docid', 'breadcrumbs', 'authors', 'keywords', 'category', 'type', 'content'}
|
||||
for spec in normalized_specs:
|
||||
qk = spec['qkey']
|
||||
qv = spec['qval']
|
||||
m = spec['mode']
|
||||
t = spec['targets']
|
||||
|
||||
# Single search box mode / global search:
|
||||
# 1. Title
|
||||
if 'title' in target_set:
|
||||
for f in ['title', 'enhancedTitle', 'pageTitle']:
|
||||
if value_matches(qval, fm.get(f)):
|
||||
matched = True
|
||||
reasons.append('Title')
|
||||
break
|
||||
# 2. DocID
|
||||
if 'docid' in target_set:
|
||||
if value_matches(qval, fm.get('docid')):
|
||||
matched = True
|
||||
reasons.append('DocID')
|
||||
# 3. Breadcrumbs
|
||||
if 'breadcrumbs' in target_set:
|
||||
bcs = fm.get('breadcrumbs') or []
|
||||
if isinstance(bcs, list) and bcs and isinstance(bcs[0], dict):
|
||||
bcs_list = [d.get('name') or d.get('slug') or '' for d in bcs]
|
||||
if not qv:
|
||||
continue # skip empty queries
|
||||
|
||||
spec_matched = False
|
||||
spec_reasons = []
|
||||
spec_snippet = ""
|
||||
|
||||
k_lower = (qk or '').strip().lower()
|
||||
if not k_lower or k_lower in ('global', 'all', 'any'):
|
||||
# Determine which targets to test
|
||||
if t:
|
||||
target_set = {x.lower() for x in t}
|
||||
else:
|
||||
bcs_list = bcs
|
||||
if '>' in qval:
|
||||
query_parts = [p.strip() for p in qval.split('>') if p.strip()]
|
||||
if match_breadcrumbs(bcs_list, query_parts):
|
||||
matched = True
|
||||
reasons.append('Breadcrumbs')
|
||||
else:
|
||||
if value_matches(qval, bcs_list):
|
||||
matched = True
|
||||
reasons.append('Breadcrumbs')
|
||||
# 4. Authors
|
||||
if 'authors' in target_set:
|
||||
if value_matches(qval, fm.get('authors')):
|
||||
matched = True
|
||||
reasons.append('Authors')
|
||||
# 5. PageKeywords
|
||||
if 'keywords' in target_set or 'pagekeywords' in target_set:
|
||||
if value_matches(qval, fm.get('pageKeywords')):
|
||||
matched = True
|
||||
reasons.append('Keywords')
|
||||
# 6. Category
|
||||
if 'category' in target_set:
|
||||
if value_matches(qval, fm.get('category')):
|
||||
matched = True
|
||||
reasons.append('Category')
|
||||
# 7. Type
|
||||
if 'type' in target_set:
|
||||
if value_matches(qval, fm.get('type')):
|
||||
matched = True
|
||||
reasons.append('Type')
|
||||
# 8. Content
|
||||
if 'content' in target_set:
|
||||
if value_matches(qval, content):
|
||||
matched = True
|
||||
reasons.append('Content')
|
||||
snippet = get_content_snippet(content, qval)
|
||||
else:
|
||||
# Specific key search
|
||||
if k_lower == 'breadcrumbs':
|
||||
bcs = fm.get('breadcrumbs') or []
|
||||
if bcs and isinstance(bcs, list) and bcs and isinstance(bcs[0], dict):
|
||||
bcs_list = [d.get('name') or d.get('slug') or '' for d in bcs]
|
||||
else:
|
||||
bcs_list = bcs
|
||||
if '>' in qval:
|
||||
query_parts = [p.strip() for p in qval.split('>') if p.strip()]
|
||||
matched = match_breadcrumbs(bcs_list, query_parts)
|
||||
else:
|
||||
matched = value_matches(qval, bcs_list)
|
||||
if matched:
|
||||
reasons.append('Breadcrumbs')
|
||||
elif k_lower == 'authors':
|
||||
matched = value_matches(qval, fm.get('authors'))
|
||||
if matched:
|
||||
reasons.append('Authors')
|
||||
elif k_lower == 'pagekeywords':
|
||||
matched = value_matches(qval, fm.get('pageKeywords'))
|
||||
if matched:
|
||||
reasons.append('Keywords')
|
||||
elif k_lower == 'content':
|
||||
matched = value_matches(qval, content)
|
||||
if matched:
|
||||
reasons.append('Content')
|
||||
snippet = get_content_snippet(content, qval)
|
||||
elif k_lower in ('title', 'enhancedtitle', 'pagetitle'):
|
||||
for f in ['title', 'enhancedTitle', 'pageTitle']:
|
||||
if value_matches(qval, fm.get(f)):
|
||||
matched = True
|
||||
reasons.append('Title')
|
||||
break
|
||||
target_set = {'title', 'docid', 'breadcrumbs', 'authors', 'keywords', 'category', 'type', 'content'}
|
||||
|
||||
# 1. Title
|
||||
if 'title' in target_set:
|
||||
for f in ['title', 'enhancedTitle', 'pageTitle']:
|
||||
if value_matches(qv, fm.get(f), m):
|
||||
spec_matched = True
|
||||
spec_reasons.append('Title')
|
||||
break
|
||||
# 2. DocID
|
||||
if 'docid' in target_set:
|
||||
if value_matches(qv, fm.get('docid'), m):
|
||||
spec_matched = True
|
||||
spec_reasons.append('DocID')
|
||||
# 3. Breadcrumbs
|
||||
if 'breadcrumbs' in target_set:
|
||||
bcs = fm.get('breadcrumbs') or []
|
||||
if isinstance(bcs, list) and bcs and isinstance(bcs[0], dict):
|
||||
bcs_list = [d.get('name') or d.get('slug') or '' for d in bcs]
|
||||
else:
|
||||
bcs_list = bcs
|
||||
if '>' in qv:
|
||||
query_parts = [p.strip() for p in qv.split('>') if p.strip()]
|
||||
if match_breadcrumbs(bcs_list, query_parts):
|
||||
spec_matched = True
|
||||
spec_reasons.append('Breadcrumbs')
|
||||
else:
|
||||
if value_matches(qv, bcs_list, m):
|
||||
spec_matched = True
|
||||
spec_reasons.append('Breadcrumbs')
|
||||
# 4. Authors
|
||||
if 'authors' in target_set:
|
||||
if value_matches(qv, fm.get('authors'), m):
|
||||
spec_matched = True
|
||||
spec_reasons.append('Authors')
|
||||
# 5. PageKeywords
|
||||
if 'keywords' in target_set or 'pagekeywords' in target_set:
|
||||
if value_matches(qv, fm.get('pageKeywords'), m):
|
||||
spec_matched = True
|
||||
spec_reasons.append('Keywords')
|
||||
# 6. Category
|
||||
if 'category' in target_set:
|
||||
if value_matches(qv, fm.get('category'), m):
|
||||
spec_matched = True
|
||||
spec_reasons.append('Category')
|
||||
# 7. Type
|
||||
if 'type' in target_set:
|
||||
if value_matches(qv, fm.get('type'), m):
|
||||
spec_matched = True
|
||||
spec_reasons.append('Type')
|
||||
# 8. Content
|
||||
if 'content' in target_set:
|
||||
if value_matches(qv, content, m):
|
||||
spec_matched = True
|
||||
spec_reasons.append('Content')
|
||||
spec_snippet = get_content_snippet(content, qv)
|
||||
else:
|
||||
matched = value_matches(qval, fm.get(qkey))
|
||||
if matched:
|
||||
reasons.append(qkey.capitalize())
|
||||
# Specific key search
|
||||
if k_lower == 'breadcrumbs':
|
||||
bcs = fm.get('breadcrumbs') or []
|
||||
if bcs and isinstance(bcs, list) and bcs and isinstance(bcs[0], dict):
|
||||
bcs_list = [d.get('name') or d.get('slug') or '' for d in bcs]
|
||||
else:
|
||||
bcs_list = bcs
|
||||
if '>' in qv:
|
||||
query_parts = [p.strip() for p in qv.split('>') if p.strip()]
|
||||
spec_matched = match_breadcrumbs(bcs_list, query_parts)
|
||||
else:
|
||||
spec_matched = value_matches(qv, bcs_list, m)
|
||||
if spec_matched:
|
||||
spec_reasons.append('Breadcrumbs')
|
||||
elif k_lower == 'authors':
|
||||
spec_matched = value_matches(qv, fm.get('authors'), m)
|
||||
if spec_matched:
|
||||
spec_reasons.append('Authors')
|
||||
elif k_lower == 'pagekeywords':
|
||||
spec_matched = value_matches(qv, fm.get('pageKeywords'), m)
|
||||
if spec_matched:
|
||||
spec_reasons.append('Keywords')
|
||||
elif k_lower == 'content':
|
||||
spec_matched = value_matches(qv, content, m)
|
||||
if spec_matched:
|
||||
spec_reasons.append('Content')
|
||||
spec_snippet = get_content_snippet(content, qv)
|
||||
elif k_lower in ('title', 'enhancedtitle', 'pagetitle'):
|
||||
for f in ['title', 'enhancedTitle', 'pageTitle']:
|
||||
if value_matches(qv, fm.get(f), m):
|
||||
spec_matched = True
|
||||
spec_reasons.append('Title')
|
||||
break
|
||||
else:
|
||||
spec_matched = value_matches(qv, fm.get(qk), m)
|
||||
if spec_matched:
|
||||
spec_reasons.append(qk.capitalize())
|
||||
|
||||
if spec_matched:
|
||||
matched = True
|
||||
spec_reasons_clean = [str(x) for x in spec_reasons]
|
||||
reasons.extend(spec_reasons_clean)
|
||||
if spec_snippet and not snippet:
|
||||
snippet = spec_snippet
|
||||
|
||||
if matched:
|
||||
out.append({
|
||||
|
||||
Reference in New Issue
Block a user