pyPreservica 2.0.3__py3-none-any.whl → 3.3.3__py3-none-any.whl

pyPreservica/contentAPI.py

@@ -10,17 +10,43 @@ licence:    Apache License 2.0
 """
 
 import csv
-from typing import Generator
+from io import BytesIO
+from typing import Generator, Callable, Optional, Union
 from pyPreservica.common import *
 
 logger = logging.getLogger(__name__)
 
+class SortOrder(Enum):
+    asc = 1
+    desc = 2
+
+class Field:
+    name: str
+    value: Optional[str]
+    operator: Optional[str]
+    sort_order: Optional[SortOrder]
+
+    def __init__(self, name: str, value: str, operator: Optional[str]=None, sort_order: Optional[SortOrder]=None):
+        self.name = name
+        self.value = value
+        self.operator = operator
+        self.sort_order = sort_order
+
+
 
 class ContentAPI(AuthenticatedAPI):
+    """
+        The ContentAPI class provides the search interface to the Preservica repository.
+
+    """
+
+
+    def __init__(self, username: str = None, password: str = None, tenant: str = None, server: str = None,
+                 use_shared_secret: bool = False, two_fa_secret_key: str = None,
+                 protocol: str = "https", request_hook: Callable = None, credentials_path: str = 'credentials.properties'):
 
-    def __init__(self, username=None, password=None, tenant=None, server=None, use_shared_secret=False,
-                 two_fa_secret_key: str = None, protocol: str = "https"):
-        super().__init__(username, password, tenant, server, use_shared_secret, two_fa_secret_key, protocol)
+        super().__init__(username, password, tenant, server, use_shared_secret, two_fa_secret_key,
+                         protocol, request_hook, credentials_path)
         self.callback = None
 
     class SearchResult:
@@ -56,7 +82,8 @@ class ContentAPI(AuthenticatedAPI):
             params = {'id': f'sdb:{entity_type.value}|{reference}'}
         else:
             params = {'id': f'sdb:{entity_type}|{reference}'}
-        request = self.session.get(f'{self.protocol}://{self.server}/api/content/object-details', params=params, headers=headers)
+        request = self.session.get(f'{self.protocol}://{self.server}/api/content/object-details', params=params,
+                                   headers=headers)
         if request.status_code == requests.codes.ok:
             return request.json()["value"]
         elif request.status_code == requests.codes.not_found:
@@ -69,6 +96,29 @@ class ContentAPI(AuthenticatedAPI):
             logger.error(f"object_details failed with error code: {request.status_code}")
             raise RuntimeError(request.status_code, f"object_details failed with error code: {request.status_code}")
 
+
+    def download_bytes(self, reference):
+        headers = {HEADER_TOKEN: self.token, 'Content-Type': 'application/octet-stream'}
+        params = {'id': f'sdb:IO|{reference}'}
+        with self.session.get(f'{self.protocol}://{self.server}/api/content/download', params=params, headers=headers,
+                              stream=True) as req:
+            if req.status_code == requests.codes.ok:
+                file_bytes = BytesIO()
+                for chunk in req.iter_content(chunk_size=CHUNK_SIZE):
+                    file_bytes.write(chunk)
+                file_bytes.seek(0)
+                return file_bytes
+            elif req.status_code == requests.codes.unauthorized:
+                self.token = self.__token__()
+                return self.download_bytes(reference)
+            elif req.status_code == requests.codes.not_found:
+                logger.error(f"The requested asset reference is not found in the repository: {reference}")
+                raise RuntimeError(reference, "The requested reference is not found in the repository")
+            else:
+                logger.error(f"download failed with error code: {req.status_code}")
+                raise RuntimeError(req.status_code, f"download failed with error code: {req.status_code}")
+
+
     def download(self, reference, filename):
         headers = {HEADER_TOKEN: self.token, 'Content-Type': 'application/octet-stream'}
         params = {'id': f'sdb:IO|{reference}'}
@@ -91,6 +141,27 @@ class ContentAPI(AuthenticatedAPI):
                 logger.error(f"download failed with error code: {req.status_code}")
                 raise RuntimeError(req.status_code, f"download failed with error code: {req.status_code}")
 
+    def thumbnail_bytes(self, entity_type, reference: str, size: Thumbnail = Thumbnail.LARGE) -> Union[BytesIO, None]:
+        headers = {HEADER_TOKEN: self.token, 'accept': 'image/png'}
+        params = {'id': f'sdb:{entity_type}|{reference}', 'size': f'{size.value}'}
+        with self.session.get(f'{self.protocol}://{self.server}/api/content/thumbnail', params=params, headers=headers, stream=True) as req:
+            if req.status_code == requests.codes.ok:
+                file_bytes = BytesIO()
+                for chunk in req.iter_content(chunk_size=CHUNK_SIZE):
+                    file_bytes.write(chunk)
+                file_bytes.seek(0)
+                return file_bytes
+            elif req.status_code == requests.codes.unauthorized:
+                self.token = self.__token__()
+                return self.thumbnail_bytes(entity_type, reference, size)
+            elif req.status_code == requests.codes.not_found:
+                logger.error(req.content.decode("utf-8"))
+                logger.error(f"The requested reference is not found in the repository: {reference}")
+                raise RuntimeError(reference, "The requested reference is not found in the repository")
+            else:
+                logger.error(f"thumbnail failed with error code: {req.status_code}")
+                raise RuntimeError(req.status_code, f"thumbnail failed with error code: {req.status_code}")
+
     def thumbnail(self, entity_type, reference, filename, size=Thumbnail.LARGE):
         headers = {HEADER_TOKEN: self.token, 'accept': 'image/png'}
         params = {'id': f'sdb:{entity_type}|{reference}', 'size': f'{size.value}'}
@@ -129,8 +200,8 @@ class ContentAPI(AuthenticatedAPI):
             logger.error(f"indexed_fields failed with error code: {results.status_code}")
             raise RuntimeError(results.status_code, f"indexed_fields failed with error code: {results.status_code}")
 
-    def simple_search_csv(self, query: str = "%", csv_file="search.csv", list_indexes: list = None):
-        page_size = 50
+    def simple_search_csv(self, query: str = "%", page_size: int = 50, csv_file="search.csv",
+                          list_indexes: list = None):
         if list_indexes is None or len(list_indexes) == 0:
             metadata_fields = ["xip.reference", "xip.title", "xip.description", "xip.document_type",
                                "xip.parent_ref", "xip.security_descriptor"]
@@ -163,7 +234,8 @@ class ContentAPI(AuthenticatedAPI):
         else:
             metadata_fields = ','.join(list_indexes)
         payload = {'start': start_from, 'max': str(page_size), 'metadata': metadata_fields, 'q': query_term}
-        results = self.session.post(f'{self.protocol}://{self.server}/api/content/search', data=payload, headers=headers)
+        results = self.session.post(f'{self.protocol}://{self.server}/api/content/search', data=payload,
+                                    headers=headers)
         results_list = []
         if results.status_code == requests.codes.ok:
             json_doc = results.json()
@@ -192,8 +264,9 @@ class ContentAPI(AuthenticatedAPI):
             logger.error(f"search failed with error code: {results.status_code}")
             raise RuntimeError(results.status_code, f"simple_search failed with error code: {results.status_code}")
 
-    def search_index_filter_csv(self, query: str = "%", csv_file="search.csv", filter_values: dict = None):
-        page_size = 50
+    def search_index_filter_csv(self, query: str = "%", csv_file="search.csv", page_size: int = 50,
+                                filter_values: dict = None,
+                                sort_values: dict = None):
         if filter_values is None:
             filter_values = {}
         if "xip.reference" not in filter_values:
@@ -205,23 +278,116 @@ class ContentAPI(AuthenticatedAPI):
         with open(csv_file, newline='', mode="wt", encoding="utf-8") as csv_file:
             writer = csv.DictWriter(csv_file, fieldnames=header_fields)
             writer.writeheader()
-            writer.writerows(self.search_index_filter_list(query, page_size, filter_values))
+            writer.writerows(self.search_index_filter_list(query, page_size, filter_values, sort_values))
 
-    def search_index_filter_list(self, query: str = "%", page_size: int = 25, filter_values: dict = None) -> Generator:
+    def search_fields(self, query: str = "%",  fields: list[Field]=None,  page_size: int = 25) -> Generator:
+        """
+        Run a search query with multiple fields
+
+        :param query: The main search query.
+        :param fields:  List of search fields
+        :param page_size:  The default search page size
+        :return: search result
+        """
+
+        if self.major_version < 7 and self.minor_version < 5:
+            raise RuntimeError("search_fields API call is not available when connected to a v7.5 System")
+
+        search_result = self._search_fields(query=query, fields=fields, start_index=0, page_size=page_size)
+        for e in search_result.results_list:
+            yield e
+        found = len(search_result.results_list)
+        while search_result.hits > found:
+            search_result = self._search_fields(query=query, fields=fields, start_index=found, page_size=page_size)
+            for e in search_result.results_list:
+                yield e
+            found = found + len(search_result.results_list)
+
+    def _search_fields(self, query: str = "%", fields: list[Field]=None, start_index: int = 0, page_size: int = 25):
+
+        start_from = str(start_index)
+        headers = {'Content-Type': 'application/x-www-form-urlencoded', HEADER_TOKEN: self.token}
+
+        if fields is None:
+            fields = []
+
+        field_list = []
+        sort_list = []
+        metadata_elements = []
+        for field in fields:
+            metadata_elements.append(field.name)
+            if field.value is None or field.value == "":
+                field_list.append('{' f' "name": "{field.name}", "values": [] ' + '}')
+            elif field.operator == "NOT":
+                field_list.append('{' f' "name": "{field.name}", "values": ["{field.value}"], "operator": "NOT" ' + '}')
+            else:
+                field_list.append('{' f' "name": "{field.name}", "values": ["{field.value}"] ' + '}')
+
+            if field.sort_order is not None:
+                sort_list.append(f'{{"sortFields": ["{field.name}"], "sortOrder": "{field.sort_order.name}"}}')
+
+
+        filter_terms = ','.join(field_list)
+
+        if len(sort_list) == 0:
+            query_term = ('{ "q":  "%s",  "fields":  [ %s ] }' % (query, filter_terms))
+        else:
+            sort_terms = ','.join(sort_list)
+            query_term = ('{ "q":  "%s",  "fields":  [ %s ],  "sort": [ %s ]}' % (query, filter_terms, sort_terms))
+
+        if len(metadata_elements) == 0:
+            metadata_elements.append("xip.title")
+
+
+        payload = {'start': start_from, 'max': str(page_size), 'metadata': list(metadata_elements), 'q': query_term}
+        logger.debug(payload)
+        results = self.session.post(f'{self.protocol}://{self.server}/api/content/search', data=payload,
+                                    headers=headers)
+        results_list = []
+        if results.status_code == requests.codes.ok:
+            json_doc = results.json()
+            metadata = json_doc['value']['metadata']
+            refs = list(json_doc['value']['objectIds'])
+            refs = list(map(lambda x: content_api_identifier_to_type(x), refs))
+            hits = int(json_doc['value']['totalHits'])
+
+            for m_row, r_row in zip(metadata, refs):
+                results_map = {'xip.reference': r_row[1]}
+                for li in m_row:
+                    results_map[li['name']] = li['value']
+                results_list.append(results_map)
+            next_start = start_index + page_size
+
+            if self.callback is not None:
+                value = str(f'{len(results_list) + start_index}:{hits}')
+                self.callback(value)
+
+            search_results = self.SearchResult(metadata, refs, hits, results_list, next_start)
+            return search_results
+        elif results.status_code == requests.codes.unauthorized:
+            self.token = self.__token__()
+            return self._search_fields(query, fields, start_index, page_size)
+        else:
+            logger.error(f"search failed with error code: {results.status_code}")
+            raise RuntimeError(results.status_code, f"search_index_filter failed")
+
+    def search_index_filter_list(self, query: str = "%", page_size: int = 25, filter_values: dict = None,
+                                 sort_values: dict = None) -> Generator:
         """
         Run a search query with optional filters
 
         :param query: The main search query.
         :param page_size:  The default search page size
         :param filter_values:  Dictionary of index names and values
+        :param sort_values:    Dictionary of sort index names and values
         :return: search result
         """
-        search_result = self._search_index_filter(query, 0, page_size, filter_values)
+        search_result = self._search_index_filter(query, 0, page_size, filter_values, sort_values)
         for e in search_result.results_list:
             yield e
         found = len(search_result.results_list)
         while search_result.hits > found:
-            search_result = self._search_index_filter(query, found, page_size, filter_values)
+            search_result = self._search_index_filter(query, found, page_size, filter_values, sort_values)
             for e in search_result.results_list:
                 yield e
             found = found + len(search_result.results_list)
@@ -249,7 +415,8 @@ class ContentAPI(AuthenticatedAPI):
         query_term = ('{ "q":  "%s",  "fields":  [ %s ] }' % (query, filter_terms))
 
         payload = {'start': start_from, 'max': str(10), 'metadata': list(filter_values.keys()), 'q': query_term}
-        results = self.session.post(f'{self.protocol}://{self.server}/api/content/search', data=payload, headers=headers)
+        results = self.session.post(f'{self.protocol}://{self.server}/api/content/search', data=payload,
+                                    headers=headers)
         if results.status_code == requests.codes.ok:
             json_doc = results.json()
             return int(json_doc['value']['totalHits'])
@@ -261,10 +428,13 @@ class ContentAPI(AuthenticatedAPI):
             raise RuntimeError(results.status_code, f"_search_index_filter_hits failed")
 
     def _search_index_filter(self, query: str = "%", start_index: int = 0, page_size: int = 25,
-                             filter_values: dict = None):
+                             filter_values: dict = None, sort_values: dict = None):
         start_from = str(start_index)
         headers = {'Content-Type': 'application/x-www-form-urlencoded', HEADER_TOKEN: self.token}
 
+        if filter_values is None:
+            filter_values = {}
+
         field_list = []
         for key, value in filter_values.items():
             if value == "":
@@ -274,11 +444,22 @@ class ContentAPI(AuthenticatedAPI):
 
         filter_terms = ','.join(field_list)
 
-        query_term = ('{ "q":  "%s",  "fields":  [ %s ] }' % (query, filter_terms))
+        if sort_values is None:
+            query_term = ('{ "q":  "%s",  "fields":  [ %s ] }' % (query, filter_terms))
+        else:
+            sort_list = []
+            for key, value in sort_values.items():
+                direction = "asc"
+                if str(value).lower().startswith("d"):
+                    direction = "desc"
+                sort_list.append(f'{{"sortFields": ["{key}"], "sortOrder": "{direction}"}}')
+            sort_terms = ','.join(sort_list)
+            query_term = ('{ "q":  "%s",  "fields":  [ %s ],  "sort": [ %s ]}' % (query, filter_terms, sort_terms))
 
         payload = {'start': start_from, 'max': str(page_size), 'metadata': list(filter_values.keys()), 'q': query_term}
         logger.debug(payload)
-        results = self.session.post(f'{self.protocol}://{self.server}/api/content/search', data=payload, headers=headers)
+        results = self.session.post(f'{self.protocol}://{self.server}/api/content/search', data=payload,
+                                    headers=headers)
         results_list = []
         if results.status_code == requests.codes.ok:
             json_doc = results.json()