Added rudimentary VSCode launch for development

.devcontainer/devcontainer.json

@@ -1,22 +0,0 @@
-// For format details, see https://aka.ms/devcontainer.json. For config options, see the
-// README at: https://github.com/devcontainers/templates/tree/main/src/python
-{
-	"name": "Python 3",
-	// Or use a Dockerfile or Docker Compose file. More info: https://containers.dev/guide/dockerfile
-	"image": "mcr.microsoft.com/devcontainers/python:1-3.12-bullseye"
-
-	// Features to add to the dev container. More info: https://containers.dev/features.
-	// "features": {},
-
-	// Use 'forwardPorts' to make a list of ports inside the container available locally.
-	// "forwardPorts": [],
-
-	// Use 'postCreateCommand' to run commands after the container is created.
-	// "postCreateCommand": "pip3 install --user -r requirements.txt",
-
-	// Configure tool-specific properties.
-	// "customizations": {},
-
-	// Uncomment to connect as root instead. More info: https://aka.ms/dev-containers-non-root.
-	// "remoteUser": "root"
-}

.vscode/launch.json

@@ -15,10 +15,7 @@
                 "${workspaceFolder}/tests/resources/groups.csv",
                 "target",
                 "replaced",
-                "-d",
+                "-d"
-                "-e",
-                "abc",
-                "-k"
             ],
             "justMyCode": true
         }

Jenkinsfile

@@ -1,20 +1,19 @@
 pipeline {
-    agent {
+    agent any
-        kubernetes {
-            cloud 'rsys-devel'
-            defaultContainer 'pip'
-            inheritFrom 'pip'
-        }
-    }
     stages {
+        stage("clean") {
+            steps {
+                sh 'rm -rf ./dist/*'
+            }
+        }
         stage("install") {
             steps {
-                sh 'pip install -r requirements.txt'
+                sh 'mamba env update --file environment.yml'
+                sh 'echo "mamba activate renamebycsv" >> ~/.bashrc'
             }
         }
         stage("build") {
             steps {
-                sh 'rm -rf ./dist/*'
                 sh "python -m build"
             }
         }
@@ -26,18 +25,17 @@ pipeline {
         }
         stage("archive") {
             steps {
-                archiveArtifacts artifacts: 'dist/*.tar.gz, dist/*.whl', fingerprint: true, followSymlinks: false, onlyIfSuccessful: true
+                archiveArtifacts artifacts: 'dist/*.tar.gz, dist/*.whl'
             }
         }
         stage("publish package") {
-            environment {
-                CREDS = credentials('rs-git-package-registry-ydeng')
-            }
             when {
                 branch '**/master'
             }
             steps {
-                sh returnStatus: true, script: 'python -m twine upload --repository-url https://git.reslate.systems/api/packages/${CREDS_USR}/pypi -u ${CREDS_USR} -p ${CREDS_PSW} --non-interactive --disable-progress-bar --verbose dist/*'
+                withCredentials([usernamePassword(credentialsId: 'rs-git-package-registry-ydeng', passwordVariable: 'PASS', usernameVariable: 'USER')]) {
+                    sh "python -m twine upload --repository-url https://git.reslate.systems/api/packages/${USER}/pypi -u ${USER} -p ${PASS} --non-interactive --disable-progress-bar --verbose dist/*"
+                }
             }
         }
     }

README.md

@@ -5,10 +5,8 @@ A simple program that renames files by using a spreadsheet in CSV format as a di
 ## Features
 
  - Rename files recursively within a directory to a desired string
- - Replace only the REGEX match portion
  - Desired string is set by a CSV where one column is the original string, and another column is the string to replace the original string with
  - Uses a REGEX capture group to select file and the portion of the filename to rename
- - Ability to define file extension
 
 ## Installing using `pip`
 
@@ -16,6 +14,7 @@ A simple program that renames files by using a spreadsheet in CSV format as a di
 
 2. Run `renamebycsv -h` to see the help and confirm installation was successful.
 
+
 ## Advanced Usage: What is REGEX?
 
 This program makes heavy use of REGEX, also known as Regular Expression to give users the flexibility to choose which portion of any given filename should be the portion used by the program to look up in the CSV. It is therefore critical for users of this script to understand how REGEX works. Here are some key pointers to get you started:
@@ -24,19 +23,9 @@ This program makes heavy use of REGEX, also known as Regular Expression to give
  - Where it differs is the ability to use one REGEX string to match many strings.
    - i.e, the REGEX "`abc\d+`" will match with "`abc1`", "`abc2`", "`abc12`", but not "`ac12`" or "`abc`".
  - Many characters can be used as normal and will match a string literally (character for character), but some will be treated as special characters (such as the previously used `\`, which indicates that the letter afterwards should be treated specially, such as a token)
-   - Common tokens to be aware of: `.` for any character, `\d` for single digits, `\w` for word characters, `\s` for space characters (tabs, spaces, linebreaks, etc.). Tokens can be repeated by using `+`, indicating "one or more", `*` indicating "none or more". If you want to match something that is read as a token by default, such as `.`, or `+`, using the `\` in front of it will cause it to match `.` literally, i.e, `1\.2` matches `1.3`, but not `123`, `1a3`, etc.
+   - Common tokens to be aware of: `.` for any character, `\d` for single digits, `\w` for word characters, `\s` for space characters (tabs, spaces, linebreaks, etc.). Tokens can be repeated by using `+`, indicating "one or more", `*` indicating "none or more".
  - A capture group is a way of "selecting" a part of a text and is formed by using `(` and `)` around the REGEX that should be selected.
 
  Now for a few examples:
 
-Let's say we have files `run325-a-1.vcf`, `run326-b-2.vcf`, and `run327-b-3.vcf`. If we know that all that matters is the `1` after the `run[numbers]-[character]-`, we can write `run\d+-\w-(\d)\.vcf` which will match with all 3 of the above examples, and select the last digit. The program can then use a given CSV to look up the selected digits and replace the name with what is given by the CSV.
+Let's say we have files `run325-a-1.vcf`, `run326-b-2.vcf`, and `run327-b-3.vcf`. If we know that all that matters is the `1` after the `run[numbers]-[character]-`, we can write `run\d+-\w-(\d).vcf` which will match with all 3 of the above examples, and select the last digit. The program can then use a given CSV to look up the selected digits and replace the name with what is given by the CSV.
-
-For learning and testing your own REGEX, checkout [regex101.com](https://regex101.com/), which allows you to write the strings that you're trying to match, and the REGEX. It will show you live which parts of the strings match to what, if any parts match.
-
-## Not Working?
-
-If the program is not working the way you would like it, try running the program in `-v DEBUG` mode which increases verbosity. Typically, files not being renamed can be attributed to one of two problems:
-
-1. It's looking in the wrong directory. The solution would be to double check that the directory it's looking in (printed by the program each run) is correct. If not, try adding quotes around the path in the command line.
-
-2. The provided REGEX pattern isn't matching to any of the files. In this case, test one or two of the files at [regex101.com](https://regex101.com/) with your pattern.

environment.yml

@@ -8,5 +8,4 @@ dependencies:
   - python=3.11
   - setuptools=67.6
   - twine=4.0
-  - cryptography=38.0.4
+  - cryptography=38.0.4
-prefix: ./env

renamebycsv/cli.py

@@ -1,29 +1,93 @@
 #!/usr/bin/env python3
 
 import argparse
+import csv
+import os
+import re
+from typing import Iterable
 import logging
 
-from renamebycsv.renamer import find_all_candidates, rename_by_csv
+
+def find_all_candidates(input_dir: str, regex: str, recursive: bool):
+    results = []
+    for subitem in os.listdir(input_dir):
+        subitem_path = os.path.join(input_dir, subitem)
+        match = re.match(regex, subitem)
+        if os.path.isdir(subitem_path) and recursive:
+            logging.debug(f'Checking directory "{subitem}"...')
+            results.extend(find_all_candidates(subitem_path, regex, recursive))
+        else:
+            if not match:
+                logging.debug(f'Ignoring "{subitem}"...')
+                continue
+            results.append((subitem_path, subitem, match))
+            logging.debug(f'Collecting "{subitem}"...')
+    return results
+
+
+def rename(
+    csv_path: str,
+    candidates: Iterable[tuple[str, str, re.Match]],
+    current: str,
+    become: str,
+    dry: bool,
+    keep_extension: bool,
+):
+    replacement_dict = {}
+    with open(csv_path, "r") as csv_fd:
+        reader = csv.reader(csv_fd)
+        current_col_ind = None
+        become_col_ind = None
+        for row in reader:
+            if current_col_ind is None and become_col_ind is None:
+                current_col_ind = row.index(current)
+                become_col_ind = row.index(become)
+                continue
+            if (
+                row[current_col_ind] in replacement_dict
+                and replacement_dict[row[current_col_ind]] != row[become_col_ind]
+            ):
+                raise Exception("Duplicate current key.")
+            replacement_dict[row[current_col_ind]] = row[become_col_ind]
+    for subitem_path, subitem, match in candidates:
+        if match.group(1) not in replacement_dict:
+            logging.warning(
+                'Group "%s" was not matched to any row in the provided CSV. '
+                "Skipping...",
+                match.group(1)
+            )
+            continue
+        original = subitem_path
+        objective = os.path.join(
+            os.path.dirname(subitem_path),
+            re.sub(match.re, replacement_dict[match.group(1)], subitem.strip()),
+        )
+        if keep_extension:
+            objective += os.path.splitext(subitem_path)[1]
+        logging.info(f'Will rename "{original}" to "{os.path.basename(objective)}"')
+        if os.path.exists(objective):
+            logging.error(
+                f'Path at "{objective}" exists, not continuing. '
+                "Use -f to overwrite instead of stopping."
+            )
+            exit(1)
+        if not dry:
+            os.rename(original, objective)
+    if dry:
+        logging.info("No file names were modified.")
 
 
 def run(args):
-    candidates = find_all_candidates(args.input_dir, args.pattern, args.recursive)
+    candidates = find_all_candidates(args.input_dir, args.regex, args.recursive)
-    if len(candidates):
+    rename(
-        rename_by_csv(
+        args.csv, candidates, args.current, args.become, args.dry, args.keep_extension
-            args.csv,
+    )
-            candidates,
-            args.current,
-            args.become,
-            args.dry,
-            args.extension,
-            args.keep_extension,
-        )
 
 
 def main():
     program_name = "renamebycsv"
     argparser = argparse.ArgumentParser(
-        program_name, description="Rename all files by using a CSV as a dictionary."
+        program_name, "Rename all files by using a CSV as a dictionary."
     )
     argparser.add_argument(
         "input_dir",
@@ -31,7 +95,7 @@ def main():
         metavar="I",
     )
     argparser.add_argument(
-        "pattern",
+        "regex",
         help="The regex to apply to each file name. The first capture group is used to "
         "perform the replacement.",
         metavar="R",
@@ -52,13 +116,13 @@ def main():
     argparser.add_argument(
         "-r",
         "--recursive",
-        help="Perform renaming action recursively.",
+        help="Perform renaming action recursively",
         action="store_true",
     )
     argparser.add_argument(
         "-f",
         "--force",
-        help="Overwrite files if file already exists.",
+        help="Overwrite files if file already exists",
         action="store_true",
     )
     argparser.add_argument(
@@ -67,28 +131,17 @@ def main():
     argparser.add_argument(
         "-V",
         "--verbosity",
-        help="Set the logging verbosity.",
+        help="Set the logging verbosity",
         required=False,
         type=str,
         default="INFO",
     )
-    argparser.add_argument(
-        "-e",
-        "--extension",
-        help='Sets the new file extension after the renaming. Use empty string ("") '
-        "to not add extension. Will use empty string by default.",
-        type=str,
-        default="",
-        required=False,
-    )
     argparser.add_argument(
         "-k",
         "--keep-extension",
-        help="Keeps the OS recognized extension from the original filename. Will "
+        help="Keeps the original file's extension by appending it to the end of the "
-        'append to end of argument given by "-e" or "--extension".',
+        "name defined by the CSV.",
         action="store_true",
-        default=False,
-        required=False,
     )
 
     args = argparser.parse_args()

renamebycsv/renamer.py

@@ -1,97 +0,0 @@
-import csv
-import logging
-import os
-import re
-from typing import Iterable
-
-
-def find_all_candidates(input_dir: str, regex: str, recursive: bool):
-    logging.info(
-        'Searching "%s" for files that match "%s" %s',
-        input_dir,
-        regex,
-        "recursively" if recursive else "non-recursively",
-    )
-    results = []
-    for subitem in os.listdir(input_dir):
-        subitem_path = os.path.join(input_dir, subitem)
-        match = re.match(regex, subitem)
-        if os.path.isdir(subitem_path) and recursive:
-            logging.debug(f'Checking directory "{subitem}"...')
-            results.extend(find_all_candidates(subitem_path, regex, recursive))
-        else:
-            if not match:
-                logging.debug(f'Ignoring "{subitem}"...')
-                continue
-            results.append((subitem_path, subitem, match))
-            logging.debug(f'Collecting "{subitem}"...')
-    if len(results) < 1:
-        logging.info(
-            'No results found matching "%s" in "%s". Please double check your REGEX '
-            "pattern and directory being searched.",
-            regex,
-            input_dir,
-        )
-    else:
-        logging.info("Collected %d files to rename.", len(results))
-    return results
-
-
-def rename_by_csv(
-    csv_path: str,
-    candidates: Iterable[tuple[str, str, re.Match]],
-    current: str,
-    become: str,
-    dry: bool,
-    extension: str,
-    keep_extension: bool,
-):
-    replacement_dict = {}
-    with open(csv_path, "r") as csv_fd:
-        reader = csv.reader(csv_fd)
-        current_col_ind = None
-        become_col_ind = None
-        for row in reader:
-            if current_col_ind is None and become_col_ind is None:
-                if current not in row:
-                    logging.error("\"%s\" not in header %s.", current, list(row))
-                if become not in row:
-                    logging.error("\"%s\" not in header %s.", become, list(row))
-                current_col_ind = row.index(current)
-                become_col_ind = row.index(become)
-                continue
-            if (
-                row[current_col_ind] in replacement_dict
-                and replacement_dict[row[current_col_ind]] != row[become_col_ind]
-            ):
-                # Check if there's a duplicate key for different values.
-                raise Exception("Duplicate current key.")
-            replacement_dict[row[current_col_ind]] = row[become_col_ind]
-    for subitem_path, subitem, match in candidates:
-        if match.group(1) not in replacement_dict:
-            logging.warning(
-                'Group "%s" was not matched to any row in the provided CSV. '
-                "Skipping...",
-                match.group(1),
-            )
-            continue
-        original = subitem_path
-        objective = os.path.join(
-            os.path.dirname(subitem_path),
-            re.sub(match.re, replacement_dict[match.group(1)], subitem.strip()),
-        )
-        if extension:
-            objective += ("." if not extension.startswith(".") else "") + extension
-        if keep_extension:
-            objective += os.path.splitext(subitem_path)[1]
-        logging.info(f'Will rename "{original}" to "{os.path.basename(objective)}"')
-        if os.path.exists(objective):
-            logging.error(
-                f'Path at "{objective}" already exists, not continuing. '
-                "Use -f to overwrite instead of stopping."
-            )
-            exit(1)
-        if not dry:
-            os.rename(original, objective)
-    if dry:
-        logging.info("No file names were modified.")

requirements.txt

@@ -1,5 +0,0 @@
-build
-pytest
-setuptools
-twine
-cryptography

setup.cfg

@@ -1,6 +1,6 @@
 [metadata]
 name = renamebycsv
-version = 0.0.8
+version = 0.0.3
 
 [options]
 packages = renamebycsv