use source course to clone

Author: asadali145

run_edx_integration_tests.sh

@@ -156,8 +156,12 @@ run_plugin_tests() {
     echo "==============Running $plugin_dir tests=================="
     cd "$plugin_dir"
 
+    # Run this plugin with CMS settings only.
+    if [[ "$plugin_dir" == *"ol_openedx_uai_content_customization"* ]]; then
+        echo "Using CMS settings only for $plugin_dir (skipping LMS run)."
+        pytest_command="pytest . --cov . --ds=cms.envs.test"
     # Check for the existence of settings/test.py
-    if [ -f "settings/test.py" ]; then
+    elif [ -f "settings/test.py" ]; then
         pytest_command="pytest . --cov . --ds=settings.test"
     else
         pytest_command="pytest . --cov . --ds=lms.envs.test"

src/ol_openedx_uai_content_customization/README.rst

@@ -22,8 +22,14 @@ Installation required in:
 Overview
 --------
 
-Original UAI courses are transformed into multiple custom courses per industry
-and length combination:
+For each unique (course_key, industry, duration) row group in the CSV the
+command clones the source course into a new UAI-specific key, removes every
+existing section from the clone, and rebuilds the content from the CSV data.
+This produces multiple industry- and length-specific variants per source
+course while preserving all course settings (grading policy, certificates,
+pacing, advanced settings) from the original.
+
+Supported industry/length combinations:
 
 +--------------+------+-------------+--------+
 | Industry     | Code | Length code | Length |
@@ -82,21 +88,23 @@ You will need two CSV files:
 1. **Customized video metadata CSV** — produced by the video customization
    workflow. Required columns:
 
-   - ``Course Key`` — the original Open edX course key (e.g.
-     ``course-v1:UAI_SOURCE+UAI.2+1T2026``)
-   - ``Industry`` — one of: ``Healthcare``, ``Finance``, ``Energy``,
+    - ``course_key`` — the Open edX course key of the **source course to
+     clone** (e.g. ``course-v1:UAI_SOURCE+UAI.2+1T2026``).  This course
+     **must already exist** in the CMS modulestore before the command runs.
+     The command validates all source keys up-front and aborts with an error
+     if any are missing.
+    - ``industry`` — one of: ``Healthcare``, ``Finance``, ``Energy``,
      ``Original industry``
-   - ``Duration (Minutes)`` — a numeric value (≤30 = Short) or the literal
-     ``long`` (= Full)
-   - ``Video File Name`` — file name matching the Name column in the assets CSV
-   - ``Video Title (Lecture Title)`` — display name for the subsection/unit/video
-   - ``Module Name`` — used to build the course display name
+    - ``duration`` — ``short`` or ``long``
+    - ``video_file_name`` — file name matching the ``name`` column in the assets CSV
+    - ``video_title`` — display name for the subsection/unit/video
+    - ``module_name`` — used to build the course display name
 
 2. **Open edX video asset CSV** — exported from Studio / OVS after uploading
    the customized videos. Required columns:
 
-   - ``Name`` — video file name (matches ``Video File Name`` above)
-   - ``Video ID`` — the Open edX UUID for the video
+    - ``name`` — video file name (matches ``video_file_name`` above)
+    - ``video_id`` — the Open edX UUID for the video
 
 Running the Command
 ~~~~~~~~~~~~~~~~~~~
@@ -129,6 +137,33 @@ Options
     Print what would be created without writing anything to the modulestore.
     Use this to verify CSV mapping before committing.
 
+How It Works
+~~~~~~~~~~~~
+
+For each unique ``(course_key, industry, duration)`` group the command:
+
+1. **Validates** all source course keys against the live modulestore before
+   making any writes (fail-fast — aborts if any source is missing).
+2. **Clones** the source course into the new UAI-specific key, inheriting all
+   course settings.
+3. **Deletes** every existing section (chapter) from the clone.
+4. **Rebuilds** the content tree from the CSV rows::
+
+       Course  (cloned — settings inherited)
+       └── Lectures  (section)
+           └── <Video Title>  (subsection)
+               └── <Video Title>  (unit)
+                   └── <Video Title>  (video block)
+
+5. **Publishes** the course.
+
+.. note::
+
+   Course creation is **not atomic** (MongoDB is not covered by Django
+   transactions).  If a run fails partway through, already-created courses
+   remain; subsequent runs will skip them with a ``DuplicateCourseError``
+   warning.
+
 Development
 -----------
 

src/ol_openedx_uai_content_customization/ol_openedx_uai_content_customization/constants.py

@@ -1,16 +1,12 @@
 """Constants for ol-openedx-uai-content-customization plugin."""
 
-# Industry short codes used in course key generation.
-# "Original industry" has no code — only a length code is appended.
 INDUSTRY_CODES = {
     "Healthcare": "HC",
     "Finance": "F",
     "Energy": "E",
     "Original industry": "",
 }
 
-# Duration label → short code used in course key generation.
-# Numeric minutes (e.g. "10") are treated as Short; "long" as Full.
 DURATION_CODE_SHORT = "S"
 DURATION_CODE_FULL = "F"
 
@@ -19,28 +15,23 @@
     "long": DURATION_CODE_FULL,
 }
 
-# Duration threshold: any numeric value at or below this (in minutes) maps to
-# "Short" (code "S"). Values above it map to "Full" (code "F").
-# The spec defines short as ≤10 min; 30 allows headroom for slightly longer
-# short-form variants without requiring a CSV format change.
-SHORT_DURATION_THRESHOLD = 30
-
-# Display name for the top-level section added to every generated course
 LECTURES_SECTION_DISPLAY_NAME = "Lectures"
 
-# CSV column names — customized video metadata CSV
-CSV_COL_COURSE_KEY = "Course Key"
-CSV_COL_INDUSTRY = "Industry"
-CSV_COL_DURATION = "duration_minutes"
-CSV_COL_VIDEO_FILE = "Video File Name"
-CSV_COL_VIDEO_TITLE = "Video Title (Lecture Title)"
-CSV_COL_MODULE_NAME = "Module Name"
+BLOCK_TYPE_CHAPTER = "chapter"
+BLOCK_TYPE_SEQUENTIAL = "sequential"
+BLOCK_TYPE_VERTICAL = "vertical"
+BLOCK_TYPE_VIDEO = "video"
+
+CSV_COL_COURSE_KEY = "course_key"
+CSV_COL_INDUSTRY = "industry"
+CSV_COL_DURATION = "duration"
+CSV_COL_VIDEO_FILE = "video_file_name"
+CSV_COL_VIDEO_TITLE = "video_title"
+CSV_COL_MODULE_NAME = "module_name"
 
-# CSV column names — Open edX video asset CSV
-CSV_COL_ASSET_NAME = "Name"
-CSV_COL_ASSET_VIDEO_ID = "Video ID"
+CSV_COL_ASSET_NAME = "name"
+CSV_COL_ASSET_VIDEO_ID = "video_id"
 
-# Required columns for each CSV — used to give early, clear error messages
 REQUIRED_CUSTOMIZED_CSV_COLS = [
     CSV_COL_COURSE_KEY,
     CSV_COL_INDUSTRY,

src/ol_openedx_uai_content_customization/ol_openedx_uai_content_customization/csv_utils.py

@@ -1,7 +1,6 @@
 """CSV parsing and video-mapping utilities for ol-openedx-uai-content-customization."""
 
 import csv
-import logging
 from collections import defaultdict
 from pathlib import Path
 
@@ -13,15 +12,10 @@
     CSV_COL_COURSE_KEY,
     CSV_COL_DURATION,
     CSV_COL_INDUSTRY,
-    DURATION_CODE_FULL,
-    DURATION_CODE_SHORT,
     DURATION_CODES,
     INDUSTRY_CODES,
-    SHORT_DURATION_THRESHOLD,
 )
 
-log = logging.getLogger(__name__)
-
 
 def parse_csv(path):
     """
@@ -33,7 +27,7 @@ def parse_csv(path):
         column header strings as they appear in the file.  Both are empty
         lists when the file contains no header row at all.
     """
-    with Path(path).open(newline="") as f:
+    with Path(path).open(encoding="utf-8", newline="") as f:
         reader = csv.DictReader(f)
         fieldnames = list(reader.fieldnames or [])
         rows = list(reader)
@@ -78,34 +72,28 @@ def resolve_duration_code(duration_value):
     """
     Convert a duration cell value into a Short/Full code.
 
-    Numeric values at or below SHORT_DURATION_THRESHOLD map to "S" (Short).
-    The literal string "long" maps to "F" (Full).
-    Any other string is checked against DURATION_CODES (case-insensitive).
+    The CSV must provide explicit values: "short" or "long"
+    (case-insensitive).
 
     Args:
         duration_value: Raw string from the Duration column.
 
     Returns:
         "S" or "F"
+
+    Raises:
+        ValueError: if the value is not one of "short" or "long".
     """
     value = str(duration_value).strip().lower()
 
     if value in DURATION_CODES:
         return DURATION_CODES[value]
 
-    try:
-        minutes = float(value)
-    except ValueError:
-        log.warning(
-            "Unrecognised duration value %r - defaulting to Short (S)", duration_value
-        )
-        return DURATION_CODE_SHORT
-    else:
-        return (
-            DURATION_CODE_SHORT
-            if minutes <= SHORT_DURATION_THRESHOLD
-            else DURATION_CODE_FULL
-        )
+    msg = (
+        "Unrecognised duration value "
+        f"{duration_value!r}. Expected one of: {', '.join(DURATION_CODES)}"
+    )
+    raise ValueError(msg)
 
 
 def build_new_course_key(original_key, industry, duration_value):