Merge pull request #39 from uic-evl/mep

Mep

Author: renambot-uic

_bibliography/README-bib.md

@@ -1 +1,41 @@
-# Do not make changes to this file, if you have additions or corrections to the EVL master bibliography make them in its repo ([https://github.com/uic-evl/evl_biblio](https://github.com/uic-evl/evl_biblio)) 
+# EVL Bibliography Directory
+
+## Important Note
+Do not make changes to this file, if you have additions or corrections to the EVL master bibliography make them in its repo ([https://github.com/uic-evl/evl_biblio](https://github.com/uic-evl/evl_biblio))
+
+## Files in this Directory
+
+### Bibliography Files
+- **papers.bib** - Main bibliography file containing all EVL publications in BibTeX format. This is synchronized from the EVL bibliography repository.
+- **papers-enhanced.bib** - Enhanced version of papers.bib with additional fields (bibtex_show, selected) added by enhanceBib.py for website display purposes
+- **sage3.bib** - SAGE3-specific bibliography file for SAGE3-related publications
+
+### Scripts
+- **enhanceBib.py** - Python script that processes BibTeX files to add website-specific fields:
+  - `bibtex_show = {true}` - enables BibTeX display on website
+  - `selected = {false}` - marks papers as selected/featured
+  - Usage: `python enhanceBib.py <bibtex_file>`
+  - Outputs: `<filename>-enhanced.bib`
+
+- **cleanbib.py** - Python script that cleans BibTeX files:
+  - Removes fields with empty values
+  - Converts abbreviated month names to full names (e.g., apr → April, jan → January)
+  - Handles both braced and unbraced month formats
+  - Usage: `python cleanbib.py <bibtex_file>`
+  - Outputs: `<filename>-updated.bib`
+
+- **checkBranches.sh** - Shell script to compare papers.bib across all git branches
+  - Shows which branches have identical versions to master
+  - Identifies branches with different versions
+  - Lists branches missing the file
+  - Useful for tracking bibliography synchronization across branches
+
+- **tidyBib.sh** - BibTeX formatting and cleanup script using bibtex-tidy
+  - Formats BibTeX files with EVL-specific configuration
+  - Removes duplicates, empty fields, and standardizes formatting
+  - Sorts entries by year and applies consistent field ordering
+  - Setup: `npm install -g bibtex-tidy`
+  - Usage: `./tidyBib.sh <file.bib>`
+
+### Documentation
+- **README-bib.md** - This file, explaining the directory structure and file purposes 

_bibliography/checkBranches.sh

@@ -0,0 +1,72 @@
+#!/bin/sh
+
+# File to compare
+targetFile="./papers.bib"
+
+echo "🔍 Comparing '$targetFile' across all branches..."
+echo "⚠️  Reminder: Run 'git fetch --all --prune' first to ensure remotes are up to date."
+echo
+
+results=$(mktemp)
+
+# Collect hash per branch
+for branch in $(git branch -a --format='%(refname:short)' | sort -u); do
+    fileHash=$(git ls-tree -r "$branch" -- "$targetFile" | awk '{print $3}')
+    if [ -n "$fileHash" ]; then
+        echo "$fileHash $branch" >> "$results"
+    else
+        echo "MISSING $branch" >> "$results"
+    fi
+done
+
+echo "===== Branches analyzed ====="
+git branch -a --format='%(refname:short)'
+echo
+
+# Get master hash
+masterHash=$(grep " master$" "$results" | awk '{print $1}')
+
+if [ -z "$masterHash" ]; then
+    echo "❌ Could not find '$targetFile' in master branch."
+    rm -f "$results"
+    exit 1
+fi
+
+echo "===== Version Groups ====="
+
+# Same as master
+sameAsMaster=$(grep "^$masterHash " "$results" | awk '{print $2}' | tr '\n' ' ')
+echo "Same as master: $sameAsMaster"
+echo
+
+# Different from master
+grep -v '^MISSING' "$results" | grep -v "^$masterHash " | awk '
+{
+    hash=$1
+    branch=$2
+    groups[hash]=groups[hash] branch " "
+}
+END {
+    if (length(groups) == 0) {
+        print "No branches differ from master."
+    } else {
+        groupNum=1
+        for (h in groups) {
+            print "Different group " groupNum ": " groups[h]
+            groupNum++
+        }
+    }
+}
+'
+echo
+
+# Missing file
+if grep -q '^MISSING' "$results"; then
+    echo "Branches missing file '$targetFile':"
+    grep '^MISSING' "$results" | cut -d' ' -f2- | tr '\n' ' '
+    echo
+fi
+
+rm -f "$results"
+echo
+echo "✅ Summary complete."

_bibliography/cleanbib.py

@@ -0,0 +1,98 @@
+#!/usr/bin/env python3
+import argparse
+import os
+import re
+
+# Mapping for month abbreviations to their full names.
+MONTH_MAPPING = {
+    'jan': 'January',
+    'january': 'January',
+    'feb': 'February',
+    'february': 'February',
+    'mar': 'March',
+    'march': 'March',
+    'apr': 'April',
+    'april': 'April',
+    'may': 'May',
+    'jun': 'June',
+    'june': 'June',
+    'jul': 'July',
+    'july': 'July',
+    'aug': 'August',
+    'august': 'August',
+    'sep': 'September',
+    'september': 'September',
+    'oct': 'October',
+    'october': 'October',
+    'nov': 'November',
+    'november': 'November',
+    'dec': 'December',
+    'december': 'December'
+}
+
+def clean_bib_file(input_file):
+    """
+    Reads the input BibTeX file line-by-line, performs two tasks:
+      1. Removes any lines defining a field with an empty value (e.g. "editor = {}").
+      2. Processes month field lines: if the month value is an abbreviated word
+         (and not numeric), it is replaced with the full month name.
+    The cleaned lines are written to a new file named <original_file>-updated.bib.
+    """
+    # Regex for an empty field line.
+    empty_field_pattern = re.compile(r'^\s*[\w\-]+\s*=\s*\{\s*\}\s*,?\s*$')
+    
+    # Regex to capture the month field.
+    # It will match a line beginning with "month", then "=", then optionally "{", then capture a complete word,
+    # then optionally "}" and optional trailing comma and whitespace.
+    # This handles both "month = apr," and "month = {apr}," formats
+    # Word boundaries ensure we only match complete month names, not substrings
+    month_field_pattern = re.compile(r'^(\s*month\s*=\s*)(\{?)(\b[a-zA-Z]+\b)(\}?)(\s*,?\s*)$', re.IGNORECASE)
+
+    with open(input_file, "r", encoding="utf-8") as f:
+        lines = f.readlines()
+
+    cleaned_lines = []
+    for line in lines:
+        # First, if the line matches an empty field, skip it.
+        if empty_field_pattern.match(line):
+            continue
+
+        # Next, if it is a month field, try to process it.
+        m = month_field_pattern.match(line)
+        if m:
+            prefix, open_brace, month_val, close_brace, suffix = m.groups()
+            # Remove extra whitespace from the month value.
+            month_val_clean = month_val.strip()
+            # If the month value is purely numeric, leave it as is.
+            if month_val_clean.isdigit():
+                cleaned_lines.append(line)
+            else:
+                # Check if it is an abbreviated month; if found, replace it.
+                lower_val = month_val_clean.lower()
+                if lower_val in MONTH_MAPPING and lower_val != MONTH_MAPPING[lower_val].lower():
+                    new_month = MONTH_MAPPING[lower_val]
+                    # Build the new line with the full month name, preserving brace style.
+                    new_line = prefix + open_brace + new_month + close_brace + suffix
+                    cleaned_lines.append(new_line)
+                else:
+                    cleaned_lines.append(line)
+        else:
+            # All other lines are left unchanged.
+            cleaned_lines.append(line)
+
+    # Build the new file name: original basename with "-updated" appended before the extension.
+    base, ext = os.path.splitext(input_file)
+    output_file = base + "-updated.bib"
+
+    with open(output_file, "w", encoding="utf-8") as f:
+        f.writelines(cleaned_lines)
+
+    print(f"Updated file created: {output_file}")
+
+if __name__ == '__main__':
+    parser = argparse.ArgumentParser(
+        description="Clean a BibTeX file by removing fields with empty values and process month fields while preserving formatting."
+    )
+    parser.add_argument("bibtex_file", help="Path to the BibTeX file to clean")
+    args = parser.parse_args()
+    clean_bib_file(args.bibtex_file)