Merge branch 'bugfix/RED-10722' into 'master'

RED-10722: fix dead letter queue

Closes RED-10722

See merge request redactmanager/cv-analysis-service!32

.gitignore

@@ -50,5 +50,3 @@ __pycache__/
 
 # unignore files
 !bom.*
-
-dotted/

.gitlab-ci.yml

@@ -12,15 +12,6 @@ variables:
   NEXUS_PROJECT_DIR: red # subfolder in Nexus docker-gin where your container will be stored
   IMAGENAME: $CI_PROJECT_NAME # if the project URL is gitlab.example.com/group-name/project-1, CI_PROJECT_NAME is project-1
 
-stages:
-  - data
-  - setup
-  - unit-tests
-  - versioning
-  - build
-  - integration-tests
-  - release
-
 pages:
   only:
     - master # KEEP THIS, necessary because `master` branch and not `main` branch

.pre-commit-config.yaml

@@ -5,10 +5,10 @@ default_language_version:
   python: python3.10
 repos:
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.5.0
+    rev: v5.0.0
     hooks:
       - id: trailing-whitespace
-      # - id: end-of-file-fixer
+      - id: end-of-file-fixer
       - id: check-yaml
         args: [--unsafe] # needed for .gitlab-ci.yml
       - id: check-toml
@@ -34,7 +34,7 @@ repos:
           - --profile black
 
   - repo: https://github.com/psf/black
-    rev: 24.3.0
+    rev: 24.10.0
     hooks:
       - id: black
         # exclude: ^(docs/|notebooks/|data/|src/secrets/)
@@ -42,7 +42,7 @@ repos:
           - --line-length=120
 
   - repo: https://github.com/compilerla/conventional-pre-commit
-    rev: v3.2.0
+    rev: v4.0.0
     hooks:
       - id: conventional-pre-commit
         pass_filenames: false

config/pyinfra.toml

@@ -1,11 +1,22 @@
+
+[asyncio]
+max_concurrent_tasks = 10
+
+[dynamic_tenant_queues]
+enabled = true
+
 [metrics.prometheus]
 enabled = true
 prefix = "redactmanager_cv_analysis_service"
 
-[tracing.opentelemetry]
+[tracing]
 enabled = true
+# possible values "opentelemetry" | "azure_monitor" (Excpects APPLICATIONINSIGHTS_CONNECTION_STRING environment variable.)
+type = "azure_monitor"
+
+[tracing.opentelemetry]
 endpoint = "http://otel-collector-opentelemetry-collector.otel-collector:4318/v1/traces"
-service_name = "redactmanager_cv_analyisis_service"
+service_name = "redactmanager_cv_analysis_service"
 exporter = "otlp"
 
 [webserver]
@@ -25,6 +36,15 @@ input_queue = "request_queue"
 output_queue = "response_queue"
 dead_letter_queue = "dead_letter_queue"
 
+tenant_event_queue_suffix = "_tenant_event_queue"
+tenant_event_dlq_suffix = "_tenant_events_dlq"
+tenant_exchange_name = "tenants-exchange"
+queue_expiration_time = 300000                                   # 5 minutes in milliseconds
+service_request_queue_prefix = "cv_analysis_request_queue"
+service_request_exchange_name = "cv_analysis_request_exchange"
+service_response_exchange_name = "cv_analysis_response_exchange"
+service_dlq_name = "cv_analysis_dlq"
+
 [storage]
 backend = "s3"
 
@@ -41,4 +61,7 @@ connection_string = ""
 
 [storage.tenant_server]
 public_key = ""
-endpoint =  "http://tenant-user-management:8081/internal-api/tenants"
+endpoint = "http://tenant-user-management:8081/internal-api/tenants"
+
+[kubernetes]
+pod_name = "test_pod"

flake.nix

@@ -15,7 +15,6 @@
         (pkgs.buildFHSUserEnv rec {
           name = "cv-analysis-service";
           targetPkgs = pkgs: (with pkgs; [
-            python310
             poppler_utils
             zlib
             poetry

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "cv-analysis-service"
-version = "2.19.0"
+version = "2.30.0"
 description = ""
 authors = ["Isaac Riley <isaac.riley@knecon.com>"]
 readme = "README.md"
@@ -25,13 +25,12 @@ coverage = "^5.5"
 dependency-check = "^0.6.0"
 lorem-text = "^2.1"
 PyMuPDF = "^1.19.6"
-pyinfra = { version = "^2.2.0", source = "gitlab-research" }
-kn-utils = { version = "0.2.7", source = "gitlab-research" }
+pyinfra = { version = "3.4.2", source = "gitlab-research" }
+kn-utils = { version = ">=0.4.0", source = "gitlab-research" }
 pdf2img = { version = "0.7.0", source = "gitlab-red" }
 dvc-azure = "^2.21.2"
 pymupdf = "^1.24.1"
 types-pillow = "^10.2.0.20240423"
-#matplotlib-backend-wezterm = "^2.1.2"
 
 [tool.poetry.group.test.dependencies]
 pytest = "^7.0.1"
@@ -77,7 +76,7 @@ priority = "explicit"
 
 [tool.pylint]
 max-line-length = 120
-docstring-min-length=4
+docstring-min-length = 4
 extension-pkg-whitelist = ["cv2"]
 extension-pkg-allow-list = ["cv2"]
 

renovate.json

@@ -1,6 +0,0 @@
-{
-  "$schema": "https://docs.renovatebot.com/renovate-schema.json",
-  "extends": [
-    "config:base"
-  ]
-}

scripts/devenvsetup.sh

@@ -0,0 +1,41 @@
+#!/bin/bash
+python_version=$1
+gitlab_user=$2
+gitlab_personal_access_token=$3
+
+# cookiecutter https://gitlab.knecon.com/knecon/research/template-python-project.git --checkout master
+# latest_dir=$(ls -td -- */ | head -n 1)  # should be the dir cookiecutter just created
+
+# cd $latest_dir
+
+pyenv install $python_version
+pyenv local $python_version
+pyenv shell $python_version
+
+# install poetry globally (PREFERRED), only need to install it once
+# curl -sSL https://install.python-poetry.org | python3 -
+
+# remember to update poetry once in a while
+poetry self update
+
+# install poetry in current python environment, can lead to multiple instances of poetry being installed on one system (DISPREFERRED)
+# pip install --upgrade pip
+# pip install poetry
+
+poetry config virtualenvs.in-project true
+poetry config installer.max-workers 10
+poetry config repositories.gitlab-research https://gitlab.knecon.com/api/v4/groups/19/-/packages/pypi
+poetry config http-basic.gitlab-research ${gitlab_user} ${gitlab_personal_access_token}
+poetry config repositories.gitlab-red https://gitlab.knecon.com/api/v4/groups/12/-/packages/pypi
+poetry config http-basic.gitlab-red ${gitlab_user} ${gitlab_personal_access_token}
+poetry config repositories.gitlab-fforesight https://gitlab.knecon.com/api/v4/groups/269/-/packages/pypi
+poetry config http-basic.gitlab-fforesight ${gitlab_user} ${gitlab_personal_access_token}
+
+poetry env use $(pyenv which python)
+poetry install --with=dev
+poetry update
+
+source .venv/bin/activate
+
+pre-commit install
+pre-commit autoupdate

scripts/grid_search.py

@@ -1,8 +0,0 @@
-from cv_analysis.table_inference import infer_lines
-
-
-def grid_search() -> None: ...
-
-
-if __name__ == "__main__":
-    grid_search()

src/cv_analysis/table_inference.py

@@ -1,6 +1,6 @@
 from operator import itemgetter
 from pathlib import Path
-from typing import Callable, Iterable, Optional, Tuple
+from typing import Callable, Optional, Tuple
 
 import cv2
 import matplotlib.pyplot as plt
@@ -9,8 +9,6 @@ from kn_utils.logging import logger  # type: ignore
 from numpy import ndarray as Array
 from scipy.stats import norm  # type: ignore
 
-from .utils.dotted_lines import detect_dotted_from_extrema
-
 
 def show_multiple(arrs: Tuple[Array], title: str = ""):
     plt.clf()
@@ -152,65 +150,16 @@ def filter_fp_col_lines(line_list: list[int], filt_sums: Array) -> list[int]:
     return line_list
 
 
-def sharpen_sums(sums: Array) -> Array:
-    sums = sums.astype("int64")
-    shift = 3
-    diffs = abs(sums[shift:-shift] - sums[2 * shift :]) + abs(sums[shift:-shift] - sums[: -2 * shift])
-    f2 = filter_array(sums, FILTERS["col"][2])
-    return diffs
-
-
-def detect_dotted_lines(
-    image: Array,
-    sums: Iterable,
-    horizontal: bool = True,
-    threshold: float = 1.0,
-    min_distance: int = 2,
-    max_distance: int = 20,
-) -> bool:
-    key = "row" if horizontal else "col"
-    naive = filter_array(sums, FILTERS[key][1])
-    naive_lines = np.where((naive[1:-1] < naive[:-2]) * (naive[1:-1] < naive[2:]) * (sums[1:-1] < 250))[0] + 1
-
-    bool_array = np.zeros(image.shape[1 - int(horizontal)])
-    for idx in naive_lines:
-        band = image[idx - 1 : idx + 2, :] if horizontal else image[:, idx - 1 : idx + 1]
-        band_sums = np.mean(band, axis=1 - int(horizontal))
-        band_sums = filter_array(band_sums, FILTERS[key][1])
-        extrema = np.where((band_sums[1:-1] < band_sums[:-2]) * (band_sums[1:-1] < band_sums[2:]))[0] + 1
-
-        distances = extrema[1:] - extrema[:-1]
-        mean = np.mean(distances)
-        std = np.std(distances)
-
-        check = "✔" if (ratio := (mean / (std + 0.01))) > 1.5 and mean < 40 else ""
-        print(f"{idx:4} {mean:6.2f}  {std:6.2f}  {ratio:6.2f} {check}")
-
-        score = std  # maybe make more advanced score function later
-        if (min_distance <= mean <= max_distance) and (score < threshold):
-            print(idx)
-            bool_array[idx] = 1
-    return bool_array
-
-
 def get_lines_either(table_array: Array, horizontal=True) -> list[int]:
     key = "row" if horizontal else "col"
-    h, w = map(int, table_array.shape)
-
-    table_array = (
-        table_array[:, int(0.1 * w) : int(0.9 * w)] if horizontal else table_array[int(0.1 * h) : int(0.9 * h)]
-    )
 
     sums = np.mean(table_array, axis=int(horizontal))
-    dotted = detect_dotted_lines(table_array, sums, horizontal=horizontal)
-
     threshold = 0.3 * 255  # np.mean(sums) - (1 + 2 * horizontal) * np.std(sums)
-    predicate = 1000.0 * ((sums < threshold) | dotted)
+    predicate = 1000.0 * (sums < threshold)
     sums = np.maximum(
         np.maximum(sums[1:-1], predicate[1:-1]),
         np.maximum(predicate[:-2], predicate[2:]),
     )
-
     filtered_sums = filter_array(sums, FILTERS[key][1])
     filtered_sums = filter_array(filtered_sums, FILTERS[key][2])
     filtered_sums = filter_array(filtered_sums, FILTERS[key][3])
@@ -230,7 +179,9 @@ def img_bytes_to_array(img_bytes: bytes) -> Array:
 
 
 def infer_lines(img: Array) -> dict[str, dict[str, int] | list[dict[str, int]]]:
+    cv2.imwrite("/tmp/table.png", img)
     _, img = cv2.threshold(img, 220, 255, cv2.THRESH_BINARY)
+    cv2.imwrite("/tmp/table_bin.png", img)
     h, w = map(int, img.shape)
     row_vals = map(int, get_lines_either(img, horizontal=True))
     col_vals = map(int, get_lines_either(img, horizontal=False))

src/cv_analysis/utils/dotted_lines.py

@@ -1,18 +0,0 @@
-"""
-General approach:
-  Get horizontal and vertical pixel sum extrema. Then take a band of k around each minimum (corresponding to darkest), e.g. k=3.
-  Recalculate minima for each band.
-  Compute a list of distances between minima.
-  Compute the mean and standard deviation between minima.
-  If rho:=std/(eta*mean) < phi for some threshold phi, the band contains a dotted line. -> logic: std can be larger for larger mean, i.e. more spaced-out dotted lines
-
-Pros:
-  Intuitive and efficient.
-
-Cons:
-  May not work for irregular/mixed dotted lines, such as (possibly) --*--*--*--*--*--*--*--*--*--*--
-"""
-
-from typing import Iterable
-
-import numpy as np