Merge pull request #7 from yangwu1227/update-schema

Update schema

README.md

@@ -38,15 +38,15 @@ This project creates an asynchronous RESTful API built with Python, FastAPI, and
     ```
 
     The payload also supports two additional optional parameters:
-    - `summarizer_specifier`: Specifies the summarization algorithm. Supported values are `lsa`, `lex_rank`, `text_rank`, and `edmundson`. If not provided, the default is `lsa`.
+    - `summarization_method`: Specifies the summarization algorithm. Supported values are `lsa`, `lex_rank`, `text_rank`, and `edmundson`. If not provided, the default is `lsa`.
     - `sentence_count`: Specifies the number of sentences in the generated summary, with a range of 5 to 30. If not provided, the default is 10.
 
     Example request with all parameters:
 
     ```bash
     curl -X POST "https://text-summarizer-d918be4fb9c8.herokuapp.com/summaries/" \
     -H "Content-Type: application/json" \
-    -d '{"url": "https://realpython.com/pointers-in-python/", "summarizer_specifier": "lex_rank", "sentence_count": 15}'
+    -d '{"url": "https://realpython.com/pointers-in-python/", "summarization_method": "lex_rank", "sentence_count": 15}'
     ```
 
     For more information on the supported summarization algorithms, see the [sumy documentation](https://github.com/miso-belica/sumy/blob/main/docs/summarizators.md).

project/app/api/crud.py

@@ -20,7 +20,12 @@ async def post(payload: SummaryPayloadSchema) -> int:
     int
         The ID of the newly created summary.
     """
-    summary = TextSummary(url=payload.url, summary="")
+    summary = TextSummary(
+        url=payload.url,
+        summary="",
+        summarization_method=payload.summarization_method,
+        sentence_count=payload.sentence_count,
+    )
     # Create/update the model object
     await summary.save()
     # Return the key

project/app/api/summaries.py

@@ -1,4 +1,4 @@
-from typing import Annotated, Dict, List
+from typing import Annotated, List
 
 from fastapi import APIRouter, BackgroundTasks, Path
 
@@ -9,7 +9,7 @@
     SummaryResponseSchema,
     SummaryUpdatePayloadSchema,
 )
-from app.models.tortoise import SummarySchema
+from app.models.tortoise import TextSummarySchema
 from app.summarizer import generate_summary
 
 router = APIRouter()
@@ -32,28 +32,28 @@ async def create_summary(
     Returns
     -------
     SummaryResponseSchema
-        The newly created summary's response, including the `url`, `id`, `summarizer_specifier`, and `sentence_count`.
+        The newly created summary's response, including the `url`, `id`, `summarization_method`, and `sentence_count`.
     """
     summary_id = await crud.post(payload)
     # Generate summary as a background task
     background_tasks.add_task(
         generate_summary,
         summary_id,
         str(payload.url),
-        payload.summarizer_specifier,
+        payload.summarization_method,
         int(payload.sentence_count),
     )
     response = SummaryResponseSchema(
         url=payload.url,
         id=summary_id,
-        summarizer_specifier=payload.summarizer_specifier,
+        summarization_method=payload.summarization_method,
         sentence_count=payload.sentence_count,
     )
     return response
 
 
-@router.get("/{id}/", response_model=SummarySchema)
-async def read_summary(id: Annotated[int, Path(title="The ID of the text summary to query", gt=0)]) -> SummarySchema:  # type: ignore
+@router.get("/{id}/", response_model=TextSummarySchema)
+async def read_summary(id: Annotated[int, Path(title="The ID of the text summary to query", gt=0)]) -> TextSummarySchema:  # type: ignore
     """
     Retrieve a single summary based on its ID (i.e., primary key).
 
@@ -64,7 +64,7 @@ async def read_summary(id: Annotated[int, Path(title="The ID of the text summary
 
     Returns
     -------
-    SummarySchema
+    TextSummarySchema
         The retrieved summary object.
 
     Raises
@@ -79,23 +79,23 @@ async def read_summary(id: Annotated[int, Path(title="The ID of the text summary
     return summary
 
 
-@router.get("/", response_model=List[SummarySchema])  # type: ignore
-async def read_all_summaries() -> List[SummarySchema]:  # type: ignore
+@router.get("/", response_model=List[TextSummarySchema])  # type: ignore
+async def read_all_summaries() -> List[TextSummarySchema]:  # type: ignore
     """
     Retrieve all summaries.
 
     Returns
     -------
-    List[SummarySchema]
+    List[TextSummarySchema]
         A list of all the summaries.
     """
     return await crud.get_all()
 
 
-@router.delete("/{id}/", response_model=SummarySchema)
+@router.delete("/{id}/", response_model=TextSummarySchema)
 async def remove_summary(
     id: Annotated[int, Path(title="The ID of the text summary to delete", gt=0)]
-) -> SummarySchema:  # type: ignore
+) -> TextSummarySchema:  # type: ignore
     """
     Delete a single summary based on its ID (i.e., primary key).
 
@@ -106,7 +106,7 @@ async def remove_summary(
 
     Returns
     -------
-    SummarySchema
+    TextSummarySchema
         The retrieved summary response containing an ID and url.
 
     Raises
@@ -124,11 +124,11 @@ async def remove_summary(
     return summary
 
 
-@router.put("/{id}/", response_model=SummarySchema)
+@router.put("/{id}/", response_model=TextSummarySchema)
 async def update_summary(
     id: Annotated[int, Path(title="The ID of the text summary to update", gt=0)],
     payload: SummaryUpdatePayloadSchema,
-) -> SummarySchema:  # type:ignore
+) -> TextSummarySchema:  # type:ignore
     """
     Update a text summary by its ID. Both the URL and the summary text are updated based on the provided payload.
 
@@ -141,7 +141,7 @@ async def update_summary(
 
     Returns
     -------
-    SummarySchema
+    TextSummarySchema
         The updated summary object if the update is successful.
 
     Raises

project/app/models/pydantic.py

@@ -3,7 +3,7 @@
 from pydantic import AnyHttpUrl, BaseModel, Field
 
 
-class SummarizerSpecifier(str, Enum):
+class SummarizationMethod(str, Enum):
     """
     Enum representing available summarizer options.
 
@@ -30,14 +30,14 @@ class SummaryPayloadSchema(BaseModel):
     url : AnyHttpUrl
         The URL of the text for which a summary will be generated. This must be a
         valid HTTP or HTTPS URL.
-    summarizer_specifier : str
+    summarization_method : str
         The name of the summarizer to be used for generating the summary.
     sentence_count : Optional[int]
         The number of sentences to include in the summary. This field is optional.
     """
 
     url: AnyHttpUrl
-    summarizer_specifier: SummarizerSpecifier = SummarizerSpecifier.lsa
+    summarization_method: SummarizationMethod = SummarizationMethod.lsa
     sentence_count: int = Field(default=10, ge=5, le=30)
 
 
@@ -58,7 +58,7 @@ class SummaryResponseSchema(SummaryPayloadSchema):
     url : AnyHttpUrl
         The URL of the text for which a summary will be generated. This must be a
         valid HTTP or HTTPS URL.
-    summarizer_specifier : str
+    summarization_method : str
         The name of the summarizer to be used for generating the summary.
     sentence_count : Optional[int]
         The number of sentences to include in the summary. This field is optional.

project/app/models/tortoise.py

@@ -27,6 +27,9 @@ class TextSummary(Model):
     id = fields.IntField(primary_key=True)
     url = fields.TextField()
     summary = fields.TextField()
+    # Allow null to handle existing records before these were added to the schema
+    summarization_method = fields.TextField(null=True)
+    sentence_count = fields.IntField(null=True)
     # Automatically set the field to now when the object is first created
     created_at = fields.DatetimeField(auto_now_add=True)
 
@@ -49,4 +52,4 @@ def __str__(self) -> str:
 in a FastAPI application. It ensures that the fields from the Tortoise ORM model are properly 
 validated when used within API endpoints.
 """
-SummarySchema = pydantic_model_creator(TextSummary)
+TextSummarySchema = pydantic_model_creator(TextSummary)

project/app/summarizer.py

@@ -8,7 +8,7 @@
 from sumy.summarizers.text_rank import TextRankSummarizer
 from sumy.utils import get_stop_words
 
-from app.models.pydantic import SummarizerSpecifier
+from app.models.pydantic import SummarizationMethod
 from app.models.tortoise import TextSummary
 
 LANGUAGE = "english"
@@ -23,7 +23,7 @@
 
 
 async def generate_summary(
-    id: int, url: str, summarizer_specifier: SummarizerSpecifier, sentence_count: int
+    id: int, url: str, summarization_method: SummarizationMethod, sentence_count: int
 ) -> None:
     """
     Create a summary of an article from a given URL using the `sumy` package. The summarization methods available include:
@@ -38,7 +38,7 @@ async def generate_summary(
         The generated id for this summary record.
     url : str
         The URL of the article to summarize.
-    summarizer_specifier : SummarizerSpecifier
+    summarization_method : SummarizationMethod
         The summarization algorithm to use.
     sentence_count : int
         The number of sentences in the summary.
@@ -55,7 +55,7 @@ async def generate_summary(
 
     try:
         # Note that this is an enum instance
-        summarizer_name = summarizer_specifier.value
+        summarizer_name = summarization_method.value
         # Parse content from the provided URL
         parser = HtmlParser.from_url(url, Tokenizer(LANGUAGE))
 

project/migrations/models/1_20240917150128_add_summarization_method_sentence_count.py

@@ -0,0 +1,13 @@
+from tortoise import BaseDBAsyncClient
+
+
+async def upgrade(db: BaseDBAsyncClient) -> str:
+    return """
+        ALTER TABLE "textsummary" ADD "summarization_method" TEXT;
+        ALTER TABLE "textsummary" ADD "sentence_count" INT;"""
+
+
+async def downgrade(db: BaseDBAsyncClient) -> str:
+    return """
+        ALTER TABLE "textsummary" DROP COLUMN "summarization_method";
+        ALTER TABLE "textsummary" DROP COLUMN "sentence_count";"""