#!/usr/bin/env oil

# Create an interface for select Unicode characters with rofi and copy it into the clipboard.
# The characters are extracted from the Unicode Character Database (https://www.unicode.org/ucd/).
# It requires a tag name or an XPath similarly used for Python's `xml.etree.ElementTree.Element.findall`.
# See the following link for more information.
# (https://docs.python.org/3/library/xml.etree.elementtree.html#xml.etree.ElementTree.Element.findall)

# Dependencies:
# * Oil shell
# * curl
# * python (at least v3.7)
# * rofi
# * awk

# Set to use Oil features and strictness.
shopt --set strict:all

var QUERY = ARGV[0]
var UCD_VERSION = "13.0.0"
var UCD_XML_URL = "https://www.unicode.org/Public/$UCD_VERSION/ucdxml/ucd.nounihan.grouped.zip"
var CACHE = ${XDG_CACHE_DIR:-$HOME/.cache/unicode-character-database}
mkdir -p $CACHE

if test ! -f $CACHE/ucd.zip {
  curl $UCD_XML_URL --output $CACHE/ucd.zip --silent
}

# The remaining thing is coded with Python because I want to use the UCD with no Unihan data and the grouped variation.
# Compared to the other variations, it is only ~6MB compared to ~55MB for the flat variation.
# Also, it requires more conditional handling than a simple shell script at this point.
# I could've made this script entirely in Python but I want to see what Oil shell is capable of.
python <<CODE | rofi -dmenu -p "Choose character" | awk '{ print $1 }' | xclip -selection clipboard
import xml.etree.ElementTree as ET

root = ET.fromstring('''$(unzip -p $CACHE/ucd.zip ucd.nounihan.grouped.xml)''')

# Print '<char>' and recurse into '<group>'.
def print_char(element):
  if element.tag == '{http://www.unicode.org/ns/2003/ucd/1.0}char':
    alias = element.get('na') if element.get('na') else element.get('na1')
    codepoint = int(element.get('cp'), 16)
    print("{code} {alias}".format(code=chr(codepoint), alias=alias))
  elif element.tag == '{http://www.unicode.org/ns/2003/ucd/1.0}group':
    for child in list(element):
      print_char(child)

valid_nodes = root.findall('${QUERY}')
for point in valid_nodes:
  print_char(point)
CODE