change name from vidocp to cv-analysis

.coveragerc

@@ -9,7 +9,7 @@ omit =
     */setup.py
     */build_venv/*
 source =
-    vidocp 
+    cv-analysis 
 relative_files = True
 data_file = .coverage
 

.gitignore

@@ -17,7 +17,7 @@ build_venv/
 /table_parsing.egg-info
 /target/
 /tests/
-/vidocp.egg-info/dependency_links.txt
-/vidocp.egg-info/PKG-INFO
-/vidocp.egg-info/SOURCES.txt
-/vidocp.egg-info/top_level.txt
+/cv-analysis.egg-info/dependency_links.txt
+/cv-analysis.egg-info/PKG-INFO
+/cv-analysis.egg-info/SOURCES.txt
+/cv-analysis.egg-info/top_level.txt

Dockerfile

@@ -1,12 +1,12 @@
 ARG BASE_ROOT="nexus.iqser.com:5001/red/"
 ARG VERSION_TAG=latest
 
-FROM ${BASE_ROOT}vidocp-base:${VERSION_TAG}
+FROM ${BASE_ROOT}cv-analysis-base:${VERSION_TAG}
 
 WORKDIR /app/service
 
 COPY ./src ./src
-COPY vidocp ./vidocp
+COPY cv-analysis ./cv-analysis
 
 RUN python3 -m pip install --upgrade pip
 RUN python3 -m pip install -e .

README.md

@@ -1,4 +1,4 @@
-# Vidocp — Visual Document Parsing
+# cv-analysis — Visual Document Parsing
 
 This repository implements computer vision based approaches for detecting and parsing visual features such as tables or
 previous redactions in documents.
@@ -6,8 +6,8 @@ previous redactions in documents.
 ## Installation
 
 ```bash
-git clone ssh://git@git.iqser.com:2222/rr/vidocp.git
-cd vidocp
+git clone ssh://git@git.iqser.com:2222/rr/cv-analysis.git
+cd cv-analysis
 
 python -m venv env
 source env/bin/activate
@@ -30,7 +30,7 @@ the specific task.
 The below snippet shows hot to find the outlines of previous redactions.
 
 ```python
-from vidocp.redaction_detection import find_redactions
+from cv_analysis.redaction_detection import find_redactions
 import pdf2image 
 import numpy as np
 
@@ -109,7 +109,7 @@ bash setup/docker.sh
 Build head image
 
 ```bash
-docker build -f Dockerfile -t vidocp . --build-arg BASE_ROOT=""
+docker build -f Dockerfile -t cv-analysis . --build-arg BASE_ROOT=""
 ```
 
 ### Usage (service)
@@ -117,7 +117,7 @@ docker build -f Dockerfile -t vidocp . --build-arg BASE_ROOT=""
 Shell 1
 
 ```bash
-docker run --rm --net=host --rm vidocp
+docker run --rm --net=host --rm cv-analysis
 ```
 
 Shell 2

bamboo-specs/src/main/java/buildjob/PlanSpec.java

@@ -33,8 +33,8 @@ import com.atlassian.bamboo.specs.model.task.ScriptTaskProperties.Location;
 @BambooSpec
 public class PlanSpec {
 
-    private static final String SERVICE_NAME = "vidocp";
-    private static final String SERVICE_NAME_BASE = "vidocp-base";
+    private static final String SERVICE_NAME = "cv-analysis";
+    private static final String SERVICE_NAME_BASE = "cv-analysis-base";
 
     private static final String SERVICE_KEY = SERVICE_NAME.toUpperCase().replaceAll("-","").replaceAll("_","");
 
@@ -72,7 +72,7 @@ public class PlanSpec {
     return new Plan(
             project(),
             SERVICE_NAME, new BambooKey(SERVICE_KEY))
-            .description("Docker build for vidocp.")
+            .description("Docker build for cv-analysis.")
             // .variables()
             .stages(new Stage("Build Stage")
               .jobs(

bamboo-specs/src/main/resources/scripts/sonar-scan.sh

@@ -35,7 +35,7 @@ then
     echo "Sonar Scan for branch: ${bamboo_planRepository_1_branch}"
     /usr/bin/sonar-scanner/bin/sonar-scanner -X\
       -Dsonar.projectKey=RED_$SERVICE_NAME \
-      -Dsonar.sources=src,vidocp \
+      -Dsonar.sources=src,cv_analysis \
       -Dsonar.host.url=https://sonarqube.iqser.com \
       -Dsonar.login=${bamboo_sonarqube_api_token_secret} \
       -Dsonar.branch.name=${bamboo_planRepository_1_branch} \
@@ -48,7 +48,7 @@ else
     echo "Sonar Scan for PR with key1: ${bamboo_repository_pr_key}"
     /usr/bin/sonar-scanner/bin/sonar-scanner \
       -Dsonar.projectKey=RED_$SERVICE_NAME \
-      -Dsonar.sources=src,vidocp \
+      -Dsonar.sources=src,cv_analysis \
       -Dsonar.host.url=https://sonarqube.iqser.com \
       -Dsonar.login=${bamboo_sonarqube_api_token_secret} \
       -Dsonar.pullrequest.key=${bamboo_repository_pr_key} \

bamboo-specs/target/classes/scripts/sonar-scan.sh

@@ -16,11 +16,11 @@ pip install -r requirements.txt
 echo "DVC pull step"
 dvc pull
 
-# echo "coverage calculation"
-# coverage run -m pytest --ignore=tests
-# echo "coverage report generation"
-# coverage report -m
-# coverage xml
+echo "coverage calculation"
+coverage run -m pytest
+echo "coverage report generation"
+coverage report -m
+coverage xml
 
 SERVICE_NAME=$1
 
@@ -35,7 +35,7 @@ then
     echo "Sonar Scan for branch: ${bamboo_planRepository_1_branch}"
     /usr/bin/sonar-scanner/bin/sonar-scanner -X\
       -Dsonar.projectKey=RED_$SERVICE_NAME \
-      -Dsonar.sources=src,vidocp \
+      -Dsonar.sources=src,cv_analysis \
       -Dsonar.host.url=https://sonarqube.iqser.com \
       -Dsonar.login=${bamboo_sonarqube_api_token_secret} \
       -Dsonar.branch.name=${bamboo_planRepository_1_branch} \
@@ -48,7 +48,7 @@ else
     echo "Sonar Scan for PR with key1: ${bamboo_repository_pr_key}"
     /usr/bin/sonar-scanner/bin/sonar-scanner \
       -Dsonar.projectKey=RED_$SERVICE_NAME \
-      -Dsonar.sources=src,vidocp \
+      -Dsonar.sources=src,cv_analysis \
       -Dsonar.host.url=https://sonarqube.iqser.com \
       -Dsonar.login=${bamboo_sonarqube_api_token_secret} \
       -Dsonar.pullrequest.key=${bamboo_repository_pr_key} \

cv_analysis/config.py

@@ -2,7 +2,7 @@
 
 
 from envyaml import EnvYAML
-from vidocp.locations import CONFIG_FILE
+from cv_analysis.locations import CONFIG_FILE
 
 
 def _get_item_and_maybe_make_dotindexable(container, item):

cv_analysis/figure_detection.py

@@ -2,12 +2,12 @@ import cv2
 import numpy as np
 from pdf2image import pdf2image
 
-from vidocp.utils.detection import detect_large_coherent_structures
-from vidocp.utils.display import show_mpl
-from vidocp.utils.draw import draw_rectangles
-from vidocp.utils.post_processing import remove_included
-from vidocp.utils.filters import is_large_enough, has_acceptable_format
-from vidocp.utils.text import remove_primary_text_regions
+from cv_analysis.utils.detection import detect_large_coherent_structures
+from cv_analysis.utils.display import show_mpl
+from cv_analysis.utils.draw import draw_rectangles
+from cv_analysis.utils.post_processing import remove_included
+from cv_analysis.utils.filters import is_large_enough, has_acceptable_format
+from cv_analysis.utils.text import remove_primary_text_regions
 
 
 def is_likely_figure(cont, min_area=5000, max_width_to_hight_ratio=6):

cv_analysis/layout_parsing.py

@@ -6,9 +6,9 @@ import cv2
 import numpy as np
 from pdf2image import pdf2image
 
-from vidocp.utils.display import show_mpl
-from vidocp.utils.draw import draw_rectangles
-from vidocp.utils.post_processing import remove_overlapping, remove_included, has_no_parent
+from cv_analysis.utils.display import show_mpl
+from cv_analysis.utils.draw import draw_rectangles
+from cv_analysis.utils.post_processing import remove_overlapping, remove_included, has_no_parent
 
 
 def is_likely_segment(rect, min_area=100):

cv_analysis/redaction_detection.py

@@ -5,9 +5,9 @@ import numpy as np
 import pdf2image
 from iteration_utilities import starfilter, first
 
-from vidocp.utils.display import show_mpl
-from vidocp.utils.draw import draw_contours
-from vidocp.utils.filters import is_large_enough, is_filled, is_boxy
+from cv_analysis.utils.display import show_mpl
+from cv_analysis.utils.draw import draw_contours
+from cv_analysis.utils.filters import is_large_enough, is_filled, is_boxy
 
 
 def is_likely_redaction(contour, hierarchy, min_area):

cv_analysis/table_parsing.py

@@ -6,11 +6,11 @@ import cv2
 import numpy as np
 from pdf2image import pdf2image
 
-from vidocp.utils.display import show_mpl
-from vidocp.utils.draw import draw_rectangles
-from vidocp.utils.post_processing import xywh_to_vecs, xywh_to_vec_rect, adjacent1d, remove_isolated
-from vidocp.utils.deskew import deskew_histbased
-from vidocp.layout_parsing import parse_layout
+from cv_analysis.utils.display import show_mpl
+from cv_analysis.utils.draw import draw_rectangles
+from cv_analysis.utils.post_processing import xywh_to_vecs, xywh_to_vec_rect, adjacent1d, remove_isolated
+from cv_analysis.utils.deskew import deskew_histbased
+from cv_analysis.layout_parsing import parse_layout
 
 
 def add_external_contours(image, img):

cv_analysis/test/config.py

@@ -0,0 +1,4 @@
+from cv_analysis.config import Config
+from cv_analysis.locations import TEST_CONFIG_FILE
+
+TEST_CONFIG = Config(TEST_CONFIG_FILE)

cv_analysis/test/unit_tests/config_test.py

@@ -1,4 +1,4 @@
-from vidocp.config import CONFIG
+from cv_analysis.config import CONFIG
 
 
 def test_config():

cv_analysis/test/unit_tests/table_test.py

@@ -1,11 +1,11 @@
 from os.path import join
 import json
 
-from vidocp.table_parsing import parse_table
-from vidocp.locations import TEST_DATA_DIR
-from vidocp.test.config import TEST_CONFIG
-from vidocp.utils.test_metrics import compute_document_score
-from vidocp.utils.preprocessing import open_pdf
+from cv_analysis.table_parsing import parse_table
+from cv_analysis.locations import TEST_DATA_DIR
+from cv_analysis.test.config import TEST_CONFIG
+from cv_analysis.utils.test_metrics import compute_document_score
+from cv_analysis.utils.preprocessing import open_pdf
 
 
 def test_table_parsing():

cv_analysis/utils/deskew.py

@@ -2,7 +2,7 @@ import numpy as np
 from scipy.ndimage import rotate as rotate_
 import cv2
 
-from vidocp.config import CONFIG
+from cv_analysis.config import CONFIG
 
 
 def rotate_straight(im: np.array, skew_angle: int) -> np.array:

cv_analysis/utils/draw.py

@@ -1,6 +1,6 @@
 import cv2
 
-from vidocp.utils import copy_and_normalize_channels
+from cv_analysis.utils import copy_and_normalize_channels
 
 
 def draw_contours(image, contours):

cv_analysis/utils/logging.py

@@ -2,7 +2,7 @@
 import sys
 import logging
 
-from vidocp.config import CONFIG
+from cv_analysis.config import CONFIG
 
 
 def get_logger():

cv_analysis/utils/preprocessing.py

@@ -3,7 +3,7 @@ import pdf2image
 from PIL import Image
 import cv2
 
-from vidocp.utils.deskew import deskew
+from cv_analysis.utils.deskew import deskew
 
 
 def preprocess_pdf_image(page):

scripts/annotate.py

@@ -1,9 +1,9 @@
 import argparse
 
-from vidocp.table_parsing import annotate_tables_in_pdf
-from vidocp.redaction_detection import annotate_redactions_in_pdf
-from vidocp.layout_parsing import annotate_layout_in_pdf
-from vidocp.figure_detection import detect_figures_in_pdf
+from cv_analysis.table_parsing import annotate_tables_in_pdf
+from cv_analysis.redaction_detection import annotate_redactions_in_pdf
+from cv_analysis.layout_parsing import annotate_layout_in_pdf
+from cv_analysis.figure_detection import detect_figures_in_pdf
 
 
 def parse_args():

scripts/client_mock.py

@@ -4,7 +4,7 @@ import json
 from multiprocessing.sharedctypes import Value
 import requests
 
-from vidocp.utils.preprocessing import open_pdf
+from cv_analysis.utils.preprocessing import open_pdf
 
 
 def parse_args():

scripts/deskew_demo.py

@@ -4,10 +4,10 @@ import numpy as np
 import pdf2image
 from PIL import Image
 
-from vidocp.utils.deskew import deskew_histbased  # , deskew_linebased
-from vidocp.utils.display import show_mpl
-from vidocp.utils.draw import draw_stats
-from vidocp.table_parsing import parse_table
+from cv_analysis.utils.deskew import deskew_histbased  # , deskew_linebased
+from cv_analysis.utils.display import show_mpl
+from cv_analysis.utils.draw import draw_stats
+from cv_analysis.table_parsing import parse_table
 
 
 def parse_args():

setup.py

@@ -3,11 +3,11 @@
 from distutils.core import setup
 
 setup(
-    name="vidocp",
+    name="cv_analysis",
     version="0.0.1",
     description="",
     author="",
     author_email="",
     url="",
-    packages=["vidocp"],
+    packages=["cv_analysis"],
 )

setup/docker.sh

@@ -9,5 +9,5 @@ python3 -m pip install --upgrade pip
 #pip install 'dvc[ssh]'
 #dvc pull
 
-docker build -f Dockerfile_base -t vidocp-base .
-docker build -f Dockerfile -t vidocp .
+docker build -f Dockerfile_base -t cv-analysis-base .
+docker build -f Dockerfile -t cv-analysis .

src/run_service.py

@@ -8,15 +8,15 @@ from prometheus_client import Counter, Gauge
 from prometheus_flask_exporter import PrometheusMetrics
 from waitress import serve
 
-from vidocp.utils import npconvert
-from vidocp.utils.preprocessing import preprocess_pdf_image  # TODO
-from vidocp.table_parsing import parse_table  # , detect_tables_in_pdf
-from vidocp.redaction_detection import find_redactions  # , detect_redactions_in_pdf
-from vidocp.layout_parsing import parse_layout  # , detect_layout_in_pdf #TODO
-from vidocp.figure_detection import detect_figures  # , detect_figures_in_pdf #TODO
-from vidocp.utils.logging import logger
-from vidocp.utils.preprocessing import open_pdf
-from vidocp.config import CONFIG
+from cv_analysis.utils import npconvert
+from cv_analysis.utils.preprocessing import preprocess_pdf_image  # TODO
+from cv_analysis.table_parsing import parse_table  # , detect_tables_in_pdf
+from cv_analysis.redaction_detection import find_redactions  # , detect_redactions_in_pdf
+from cv_analysis.layout_parsing import parse_layout  # , detect_layout_in_pdf #TODO
+from cv_analysis.figure_detection import detect_figures  # , detect_figures_in_pdf #TODO
+from cv_analysis.utils.logging import logger
+from cv_analysis.utils.preprocessing import open_pdf
+from cv_analysis.config import CONFIG
 
 
 def suppress_user_warnings():
@@ -30,9 +30,9 @@ def main():
 
 
 def run_server():
-    file_counter = Counter("vidocp_file_counter", "count processed files")
-    # page_counter = Counter("vidocp_page_counter", "count pages from processed files")
-    ram_metric = Gauge("vidocp_memory_usage", "Memory usage in Mb")
+    file_counter = Counter("cv_analysis_file_counter", "count processed files")
+    # page_counter = Counter("cv-analysis_page_counter", "count pages from processed files")
+    ram_metric = Gauge("cv_analysis_memory_usage", "Memory usage in Mb")
 
     def start_monitoring():
         file_counter.inc()
@@ -146,19 +146,19 @@ def annotate(task):
 
 
 def make_art():
-    art = """
-    
-    =================================================================================================
-    ==  ====  ==============       =================       ==========================================
-    ==  ====  ==============  ====  ================  ====  =========================================
-    ==  ====  ==============  ====  ================  ====  =========================================
-    ==  ====  ==  ==      ==  ====  ===   ====   ===  ====  ===   ===  =   ====   ====   ===  =   ===
-    ==   ==   ==========  ==  ====  ==     ==  =  ==       ===  =  ==    =  ==  =  ==  =  ==    =  ==
-    ===  ==  ===  =====  ===  ====  ==  =  ==  =====  ===========  ==  ========  ====     ==  =======
-    ===  ==  ===  ====  ====  ====  ==  =  ==  =====  =========    ==  =========  ===  =====  =======
-    ====    ====  ===  =====  ====  ==  =  ==  =  ==  ========  =  ==  =======  =  ==  =  ==  =======
-    =====  =====  ==      ==       ====   ====   ===  =========    ==  ========   ====   ===  =======
-    =================================================================================================
+    art = r"""
+                                                           __                      __           
+                                                          |  \                    |  \          
+  _______  __     __          ______   _______    ______  | $$ __    __   _______  \$$  _______ 
+ /       \|  \   /  \ ______ |      \ |       \  |      \ | $$|  \  |  \ /       \|  \ /       \
+|  $$$$$$$ \$$\ /  $$|      \ \$$$$$$\| $$$$$$$\  \$$$$$$\| $$| $$  | $$|  $$$$$$$| $$|  $$$$$$$
+| $$        \$$\  $$  \$$$$$$/      $$| $$  | $$ /      $$| $$| $$  | $$ \$$    \ | $$ \$$    \ 
+| $$_____    \$$ $$         |  $$$$$$$| $$  | $$|  $$$$$$$| $$| $$__/ $$ _\$$$$$$\| $$ _\$$$$$$\
+ \$$     \    \$$$           \$$    $$| $$  | $$ \$$    $$| $$ \$$    $$|       $$| $$|       $$
+  \$$$$$$$     \$             \$$$$$$$ \$$   \$$  \$$$$$$$ \$$ _\$$$$$$$ \$$$$$$$  \$$ \$$$$$$$ 
+                                                              |  \__| $$                        
+                                                               \$$    $$                        
+                                                                \$$$$$$                         
 
 """
     return art

vidocp/test/config.py

@@ -1,4 +0,0 @@
-from vidocp.config import Config
-from vidocp.locations import TEST_CONFIG_FILE
-
-TEST_CONFIG = Config(TEST_CONFIG_FILE)