ML-21: Classify API errors as transient vs permanent

This commit is contained in:
Claudio Ortolina
2026-04-24 13:55:00 +01:00
parent be4f4686f8
commit a1c665b490
43 changed files with 1429 additions and 135 deletions
+50 -16
View File
@@ -1,14 +1,23 @@
defmodule Wikipedia.API do
@moduledoc """
Interface to the Wikidata and Wikipedia APIs.
Two API surfaces are used, with different error handling:
* **Action API** (`/w/api.php`) returns HTTP 200 with an `{"error": {...}}`
payload on failure. `parse_error/1` promotes those bodies into
`Wikipedia.API.ErrorResponse` errors.
* **REST v1 API** (`/api/rest_v1/page/summary/:title`) uses classic HTTP
status codes. `parse_error/1` handles non-2xx statuses the same way.
"""
alias Req.Request
alias Wikipedia.API.ErrorResponse
require Logger
@spec get_wikipedia_title(String.t(), Wikipedia.Config.t()) ::
{:ok, String.t() | nil} | {:error, term()}
{:ok, String.t() | nil} | {:error, ErrorResponse.t() | Exception.t()}
def get_wikipedia_title(wikidata_id, config) do
case config
|> new_request("https://www.wikidata.org")
@@ -32,7 +41,8 @@ defmodule Wikipedia.API do
end
end
@spec get_article_summary(String.t(), Wikipedia.Config.t()) :: {:ok, map()} | {:error, term()}
@spec get_article_summary(String.t(), Wikipedia.Config.t()) ::
{:ok, map()} | {:error, ErrorResponse.t() | Exception.t()}
def get_article_summary(title, config) do
config
|> new_request("https://en.wikipedia.org")
@@ -41,7 +51,7 @@ defmodule Wikipedia.API do
end
@spec get_article_extract(String.t(), Wikipedia.Config.t()) ::
{:ok, String.t() | nil} | {:error, term()}
{:ok, String.t() | nil} | {:error, ErrorResponse.t() | Exception.t()}
def get_article_extract(title, config) do
case config
|> new_request("https://en.wikipedia.org")
@@ -80,16 +90,22 @@ defmodule Wikipedia.API do
|> Request.merge_options(config.req_options)
|> Req.RateLimiter.attach(name: :wikipedia, cooldown: config.api_cooldown)
|> Request.append_request_steps(log_attempt: &log_attempt/1)
|> Request.append_response_steps(log_error: &log_error/1)
|> Request.append_response_steps(parse_error: &parse_error/1)
end
defp get_request(request) do
case Req.get(request) do
{:ok, response} when response.status == 200 ->
{:ok, response.body}
{:ok, %{status: 200, body: %ErrorResponse{} = error}} ->
{:error, error}
{:ok, response} ->
{:error, response.body}
{:ok, %{status: status, body: body}} when status in 200..299 ->
{:ok, body}
{:ok, %{body: %ErrorResponse{} = error}} ->
{:error, error}
{:ok, %{body: body}} ->
{:error, body}
error ->
error
@@ -102,14 +118,32 @@ defmodule Wikipedia.API do
request
end
defp log_error({request, response}) do
if response.status in 400..499 or response.status in 500..599 do
Logger.error(fn ->
url = URI.to_string(request.url)
"Failed to fetch data from #{url}, reason: #{inspect(response.body)}"
end)
end
# Action API: HTTP 200 with an error envelope in the body.
defp parse_error(
{request,
%{status: 200, body: %{"error" => %{"code" => _, "info" => _}} = body} = response}
) do
error = ErrorResponse.from_action_api_body(body)
{request, response}
Logger.error(fn ->
url = URI.to_string(request.url)
"Failed to fetch data from #{url}, code: #{error.code}, info: #{error.message}"
end)
Request.halt(request, %{response | body: error})
end
# REST v1 API and other non-2xx responses.
defp parse_error({request, %{status: status} = response}) when status not in 200..299 do
error = ErrorResponse.from_response(response)
Logger.error(fn ->
url = URI.to_string(request.url)
"Failed to fetch data from #{url}, status: #{status}, reason: #{inspect(response.body)}"
end)
Request.halt(request, %{response | body: error})
end
defp parse_error(tuple), do: tuple
end
+94
View File
@@ -0,0 +1,94 @@
defmodule Wikipedia.API.ErrorResponse do
@moduledoc """
Structured error response for Wikipedia/Wikidata API calls.
Wikipedia exposes two API surfaces with different error paradigms:
* **Action API** (`/w/api.php`, used by `get_wikipedia_title/2` and
`get_article_extract/2`) returns **HTTP 200 with an error in the body**:
`%{"error" => %{"code" => ..., "info" => ...}}`. Without body inspection
the error would be silently returned as `{:ok, body}`.
* **REST v1 API** (`/api/rest_v1/page/summary/:title`, used by
`get_article_summary/2`) uses classic HTTP status codes.
`from_response/1` handles both paths. `from_action_api_body/1` is a dedicated
entry point for the HTTP 200 + body-error case.
## Non-error body shapes
These are NOT errors and should continue to return `{:ok, body}`:
* `%{"entities" => %{_id => %{"missing" => ""}}}` from `wbgetentities` —
the facade converts this to `{:error, :no_english_wikipedia}` at a
higher level.
* `get_in(body, ["query", "pages", _, "extract"])` returning `nil` — a
title exists but has no extract.
The discriminator for an actual error is the literal top-level `"error"` key
whose value is a map with both `"code"` and `"info"`.
"""
@behaviour MusicLibrary.ErrorResponse
alias MusicLibrary.HttpError
@type t :: %__MODULE__{
status: integer() | nil,
code: String.t() | nil,
message: String.t() | nil,
kind: HttpError.kind(),
body: term()
}
defstruct [:status, :code, :message, :kind, :body]
@spec from_response(Req.Response.t() | map()) :: t()
def from_response(%{status: status, body: body} = _response) do
%__MODULE__{
status: status,
code: extract_rest_code(body),
message: extract_rest_message(body),
kind: HttpError.default_kind(status),
body: body
}
end
@spec from_action_api_body(map()) :: t()
def from_action_api_body(%{"error" => %{"code" => code, "info" => info}} = body) do
%__MODULE__{
status: 200,
code: code,
message: info,
kind: action_api_kind(code),
body: body
}
end
@impl MusicLibrary.ErrorResponse
@spec retryable?(t()) :: boolean()
def retryable?(%__MODULE__{kind: kind}) when kind in [:rate_limit, :server_error, :timeout],
do: true
def retryable?(%__MODULE__{}), do: false
@impl MusicLibrary.ErrorResponse
@spec retry_delay_seconds(t()) :: pos_integer()
def retry_delay_seconds(%__MODULE__{kind: :rate_limit}), do: 30
def retry_delay_seconds(%__MODULE__{kind: :server_error}), do: 30
def retry_delay_seconds(%__MODULE__{kind: :timeout}), do: 10
def retry_delay_seconds(%__MODULE__{}), do: 30
defp action_api_kind("ratelimited"), do: :rate_limit
defp action_api_kind("maxlag"), do: :rate_limit
defp action_api_kind("readonly"), do: :server_error
defp action_api_kind("internal_api_error_" <> _), do: :server_error
defp action_api_kind(_), do: :client_error
defp extract_rest_code(%{"httpCode" => code}), do: to_string(code)
defp extract_rest_code(_), do: nil
defp extract_rest_message(%{"messageTranslations" => %{"en" => msg}}), do: msg
defp extract_rest_message(%{"detail" => msg}) when is_binary(msg), do: msg
defp extract_rest_message(_), do: nil
end