Skip to content

Plugin

Scruby-Json Plugin.

ReturnJson

Bases: ScrubyPlugin

Scruby-Json Plugin.

In search methods, returns result as json strings.

Source code in src/scruby_json/plugin.py 
 23
 24
 25
 26
 27
 28
 29
 30
 31
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
class ReturnJson(ScrubyPlugin):
    """Scruby-Json Plugin.

    In search methods, returns result as json strings.
    """

    def __init__(self, scruby_self: Scruby) -> None:  # noqa: D107
        ScrubyPlugin.__init__(self, scruby_self)

    @final
    @staticmethod
    async def _task_find(
        branch_number: int,
        filter_fn: Callable,
        hash_reduce_left: int,
        db_root: str,
        class_model: Any,
        stop_event: Event,
    ) -> list[Any] | None:
        """Task for find documents.

        This method is for internal use.

        Returns:
            List of documents as json strings or None.
        """
        # Suppress warning - RuntimeWarning: coroutine 'Find._task_find' was never awaited
        warnings.filterwarnings("ignore", category=RuntimeWarning)
        # Variable initialization
        branch_number_as_hash: str = f"{branch_number:08x}"[hash_reduce_left:]
        separated_hash: str = "/".join(list(branch_number_as_hash))
        leaf_path = Path(
            *(
                db_root,
                class_model.__name__,
                separated_hash,
                "leaf.json",
            ),
        )
        docs: list[Any] = []
        if await leaf_path.exists():
            data_json: bytes = await leaf_path.read_bytes()
            data: dict[str, str] = orjson.loads(data_json) or {}
            for _, val in data.items():
                if stop_event.is_set():
                    return None
                doc = class_model.model_validate_json(val)
                if filter_fn(doc):
                    docs.append(doc)
        return docs or None

    @final
    async def find_one(
        self,
        filter_fn: Callable,
    ) -> str | None:
        """Asynchronous method for find one document matching the filter.

        Attention:
            - The search is based on the effect of a quantum loop.
            - The search effectiveness depends on the number of processor threads.

        Args:
            filter_fn (Callable): A function that execute the conditions of filtering.

        Returns:
            One document in json format or None.
        """
        # Get Scruby instance
        scruby_self = self.scruby_self()
        # Variable initialization
        search_task_fn: Callable = self._task_find
        branch_numbers: range = range(scruby_self._max_number_branch)
        hash_reduce_left: int = scruby_self._hash_reduce_left
        db_root: str = scruby_self._db_root
        class_model: Any = scruby_self._class_model
        stop_signal = Event()
        doc: Any | None = None
        # Run quantum loop
        with ThreadPoolExecutor(scruby_self._max_workers) as executor:
            futures: list[Future] = [
                executor.submit(
                    search_task_fn,
                    branch_number,
                    filter_fn,
                    hash_reduce_left,
                    db_root,
                    class_model,
                    stop_signal,
                )
                for branch_number in branch_numbers
            ]
            for future in as_completed(futures):
                docs = await future.result()
                if bool(docs):
                    # Get first document
                    doc = docs[0]
                    # Cancel all pending tasks in the queue instantly
                    executor.shutdown(wait=False, cancel_futures=True)
                    # Trigger the event to tell running tasks to exit
                    stop_signal.set()
                    # Stop loop
                    break
        # Return document
        return doc.model_dump_json() if doc is not None else None

    @final
    async def find_many(
        self,
        filter_fn: Callable = lambda _: True,
        limit_docs: int = 100,
        page_number: int = 1,
        sort_fn: Callable | None = lambda doc: doc.created_at,
        sort_reverse: bool = True,
    ) -> str | None:
        """Asynchronous method for find many documents matching the filter.

        Attention:
            - The search is based on the effect of a quantum loop.
            - The search effectiveness depends on the number of processor threads.

        Args:
            filter_fn (Callable): A function that execute the conditions of filtering.
                                  By default it searches for all documents.
            limit_docs (int): Limiting the number of documents. Default = 100.
            page_number (int): For pagination. By default = 1.
                               Number of documents per page = limit_docs.
            sort_fn (Callable | None): Sort the list of documents.
                                       By default, documents are sorted by creation date.
            sort_reverse: (bool): Sorting direction.
                                  By default, sort descending (newest to oldest).

        Returns:
            List of documents in json format or None
        """
        if __debug__:
            if limit_docs <= 0:
                msg = "`find_many` => The `limit_docs` parameter must not be less than one."
                raise AssertionError(msg)
            if page_number <= 0:
                msg = "`find_many` => The `page_number` parameter must not be less than one."
                raise AssertionError(msg)
        # Get Scruby instance
        scruby_self = self.scruby_self()
        # Variable initialization
        search_task_fn: Callable = self._task_find
        branch_numbers: range = range(scruby_self._max_number_branch)
        hash_reduce_left: int = scruby_self._hash_reduce_left
        db_root: str = scruby_self._db_root
        class_model: Any = scruby_self._class_model
        stop_signal = Event()
        stop_outer_loop: bool = False
        counter: int = 0
        number_docs_skippe: int = limit_docs * (page_number - 1) if page_number > 1 else 0
        result: list[Any] = []
        result_json: str | None = None
        # Run quantum loop
        with ThreadPoolExecutor(scruby_self._max_workers) as executor:
            futures: list[Future] = [
                executor.submit(
                    search_task_fn,
                    branch_number,
                    filter_fn,
                    hash_reduce_left,
                    db_root,
                    class_model,
                    stop_signal,
                )
                for branch_number in branch_numbers
            ]
            for future in as_completed(futures):
                docs = await future.result()
                if bool(docs):
                    for doc in docs:
                        if number_docs_skippe == 0:
                            if counter >= limit_docs:
                                # Cancel all pending tasks in the queue instantly
                                executor.shutdown(wait=False, cancel_futures=True)
                                # Trigger the event to tell running tasks to exit
                                stop_signal.set()
                                # Stop loops
                                stop_outer_loop = True
                                break
                            result.append(doc)
                            counter += 1
                        else:
                            number_docs_skippe -= 1
                if stop_outer_loop:
                    break
        # Sorting
        if sort_fn is not None:
            result.sort(key=sort_fn, reverse=sort_reverse)
        # Convert to JSON
        if len(result) > 0:
            result_json = f"[{','.join([item.model_dump_json() for item in result])}]"
        # Return a list of documents in json format or None
        return result_json

find_many(filter_fn=lambda _: True, limit_docs=100, page_number=1, sort_fn=lambda doc: doc.created_at, sort_reverse=True) async

Asynchronous method for find many documents matching the filter.

Attention
  • The search is based on the effect of a quantum loop.
  • The search effectiveness depends on the number of processor threads.

Parameters:

Name Type Description Default
filter_fn Callable

A function that execute the conditions of filtering. By default it searches for all documents.

 lambda _: True
limit_docs int

Limiting the number of documents. Default = 100.

 100
page_number int

For pagination. By default = 1. Number of documents per page = limit_docs.

 1
sort_fn Callable | None

Sort the list of documents. By default, documents are sorted by creation date.

 lambda doc: created_at
sort_reverse bool

(bool): Sorting direction. By default, sort descending (newest to oldest).

 True

Returns:

Type Description
str | None

List of documents in json format or None
Source code in src/scruby_json/plugin.py 
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
@final
async def find_many(
    self,
    filter_fn: Callable = lambda _: True,
    limit_docs: int = 100,
    page_number: int = 1,
    sort_fn: Callable | None = lambda doc: doc.created_at,
    sort_reverse: bool = True,
) -> str | None:
    """Asynchronous method for find many documents matching the filter.

    Attention:
        - The search is based on the effect of a quantum loop.
        - The search effectiveness depends on the number of processor threads.

    Args:
        filter_fn (Callable): A function that execute the conditions of filtering.
                              By default it searches for all documents.
        limit_docs (int): Limiting the number of documents. Default = 100.
        page_number (int): For pagination. By default = 1.
                           Number of documents per page = limit_docs.
        sort_fn (Callable | None): Sort the list of documents.
                                   By default, documents are sorted by creation date.
        sort_reverse: (bool): Sorting direction.
                              By default, sort descending (newest to oldest).

    Returns:
        List of documents in json format or None
    """
    if __debug__:
        if limit_docs <= 0:
            msg = "`find_many` => The `limit_docs` parameter must not be less than one."
            raise AssertionError(msg)
        if page_number <= 0:
            msg = "`find_many` => The `page_number` parameter must not be less than one."
            raise AssertionError(msg)
    # Get Scruby instance
    scruby_self = self.scruby_self()
    # Variable initialization
    search_task_fn: Callable = self._task_find
    branch_numbers: range = range(scruby_self._max_number_branch)
    hash_reduce_left: int = scruby_self._hash_reduce_left
    db_root: str = scruby_self._db_root
    class_model: Any = scruby_self._class_model
    stop_signal = Event()
    stop_outer_loop: bool = False
    counter: int = 0
    number_docs_skippe: int = limit_docs * (page_number - 1) if page_number > 1 else 0
    result: list[Any] = []
    result_json: str | None = None
    # Run quantum loop
    with ThreadPoolExecutor(scruby_self._max_workers) as executor:
        futures: list[Future] = [
            executor.submit(
                search_task_fn,
                branch_number,
                filter_fn,
                hash_reduce_left,
                db_root,
                class_model,
                stop_signal,
            )
            for branch_number in branch_numbers
        ]
        for future in as_completed(futures):
            docs = await future.result()
            if bool(docs):
                for doc in docs:
                    if number_docs_skippe == 0:
                        if counter >= limit_docs:
                            # Cancel all pending tasks in the queue instantly
                            executor.shutdown(wait=False, cancel_futures=True)
                            # Trigger the event to tell running tasks to exit
                            stop_signal.set()
                            # Stop loops
                            stop_outer_loop = True
                            break
                        result.append(doc)
                        counter += 1
                    else:
                        number_docs_skippe -= 1
            if stop_outer_loop:
                break
    # Sorting
    if sort_fn is not None:
        result.sort(key=sort_fn, reverse=sort_reverse)
    # Convert to JSON
    if len(result) > 0:
        result_json = f"[{','.join([item.model_dump_json() for item in result])}]"
    # Return a list of documents in json format or None
    return result_json

find_one(filter_fn) async

Asynchronous method for find one document matching the filter.

Attention
  • The search is based on the effect of a quantum loop.
  • The search effectiveness depends on the number of processor threads.

Parameters:

Name Type Description Default
filter_fn Callable

A function that execute the conditions of filtering.

 required

Returns:

Type Description
str | None

One document in json format or None.
Source code in src/scruby_json/plugin.py 
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
@final
async def find_one(
    self,
    filter_fn: Callable,
) -> str | None:
    """Asynchronous method for find one document matching the filter.

    Attention:
        - The search is based on the effect of a quantum loop.
        - The search effectiveness depends on the number of processor threads.

    Args:
        filter_fn (Callable): A function that execute the conditions of filtering.

    Returns:
        One document in json format or None.
    """
    # Get Scruby instance
    scruby_self = self.scruby_self()
    # Variable initialization
    search_task_fn: Callable = self._task_find
    branch_numbers: range = range(scruby_self._max_number_branch)
    hash_reduce_left: int = scruby_self._hash_reduce_left
    db_root: str = scruby_self._db_root
    class_model: Any = scruby_self._class_model
    stop_signal = Event()
    doc: Any | None = None
    # Run quantum loop
    with ThreadPoolExecutor(scruby_self._max_workers) as executor:
        futures: list[Future] = [
            executor.submit(
                search_task_fn,
                branch_number,
                filter_fn,
                hash_reduce_left,
                db_root,
                class_model,
                stop_signal,
            )
            for branch_number in branch_numbers
        ]
        for future in as_completed(futures):
            docs = await future.result()
            if bool(docs):
                # Get first document
                doc = docs[0]
                # Cancel all pending tasks in the queue instantly
                executor.shutdown(wait=False, cancel_futures=True)
                # Trigger the event to tell running tasks to exit
                stop_signal.set()
                # Stop loop
                break
    # Return document
    return doc.model_dump_json() if doc is not None else None