It would seem that I have far too much time on my hands. After the post about a Star Trek “test”, I started wondering if there could be any data to back it up and… well here we go:

Those Old Scientists

Name Total Lines Percentage of Lines
KIRK 8257 32.89
SPOCK 3985 15.87
MCCOY 2334 9.3
SCOTT 912 3.63
SULU 634 2.53
UHURA 575 2.29
CHEKOV 417 1.66

The Next Generation

Name Total Lines Percentage of Lines
PICARD 11175 20.16
RIKER 6453 11.64
DATA 5599 10.1
LAFORGE 3843 6.93
WORF 3402 6.14
TROI 2992 5.4
CRUSHER 2833 5.11
WESLEY 1285 2.32

Deep Space Nine

Name Total Lines Percentage of Lines
SISKO 8073 13.0
KIRA 5112 8.23
BASHIR 4836 7.79
O’BRIEN 4540 7.31
ODO 4509 7.26
QUARK 4331 6.98
DAX 3559 5.73
WORF 1976 3.18
JAKE 1434 2.31
GARAK 1420 2.29
NOG 1247 2.01
ROM 1172 1.89
DUKAT 1091 1.76
EZRI 953 1.53

Voyager

Name Total Lines Percentage of Lines
JANEWAY 10238 17.7
CHAKOTAY 5066 8.76
EMH 4823 8.34
PARIS 4416 7.63
TUVOK 3993 6.9
KIM 3801 6.57
TORRES 3733 6.45
SEVEN 3527 6.1
NEELIX 2887 4.99
KES 1189 2.06

Enterprise

Name Total Lines Percentage of Lines
ARCHER 6959 24.52
T’POL 3715 13.09
TUCKER 3610 12.72
REED 2083 7.34
PHLOX 1621 5.71
HOSHI 1313 4.63
TRAVIS 1087 3.83
SHRAN 358 1.26

Discovery

Important Note: As the source material is incomplete for Discovery, the following table only includes line counts from seasons 1 and 4 along with a single episode of season 2.

Name Total Lines Percentage of Lines
BURNHAM 2162 22.92
SARU 773 8.2
BOOK 586 6.21
STAMETS 513 5.44
TILLY 488 5.17
LORCA 471 4.99
TARKA 313 3.32
TYLER 300 3.18
GEORGIOU 279 2.96
CULBER 267 2.83
RILLAK 205 2.17
DETMER 186 1.97
OWOSEKUN 169 1.79
ADIRA 154 1.63
COMPUTER 152 1.61
ZORA 151 1.6
VANCE 101 1.07
CORNWELL 101 1.07
SAREK 100 1.06
T’RINA 96 1.02

If anyone is interested, here’s the (rather hurried, don’t judge me) Python used:

#!/usr/bin/env python

#
# This script assumes that you've already downloaded all the episode lines from
# the fantastic chakoteya.net:
#
# wget --accept=html,htm --relative --wait=2 --include-directories=/STDisco17/ http://www.chakoteya.net/STDisco17/episodes.html -m
# wget --accept=html,htm --relative --wait=2 --include-directories=/Enterprise/ http://www.chakoteya.net/Enterprise/episodes.htm -m
# wget --accept=html,htm --relative --wait=2 --include-directories=/Voyager/ http://www.chakoteya.net/Voyager/episode_listing.htm -m
# wget --accept=html,htm --relative --wait=2 --include-directories=/DS9/ http://www.chakoteya.net/DS9/episodes.htm -m
# wget --accept=html,htm --relative --wait=2 --include-directories=/NextGen/ http://www.chakoteya.net/NextGen/episodes.htm -m
# wget --accept=html,htm --relative --wait=2 --include-directories=/StarTrek/ http://www.chakoteya.net/StarTrek/episodes.htm -m
#
# Then you'll probably have to convert the following files to UTF-8 as they
# differ from the rest:
#
# * Voyager/709.htm
# * Voyager/515.htm
# * Voyager/416.htm
# * Enterprise/41.htm
#

import re
from collections import defaultdict
from pathlib import Path

EPISODE_REGEX = re.compile(r"^\d+\.html?$")
LINE_REGEX = re.compile(r"^(?P<name>[A-Z']+): ")

EPISODES = Path("www.chakoteya.net")
DISCO = EPISODES / "STDisco17"
ENT = EPISODES / "Enterprise"
TNG = EPISODES / "NextGen"
TOS = EPISODES / "StarTrek"
DS9 = EPISODES / "DS9"
VOY = EPISODES / "Voyager"

NAMES = {
    TOS.name: "Those Old Scientists",
    TNG.name: "The Next Generation",
    DS9.name: "Deep Space Nine",
    VOY.name: "Voyager",
    ENT.name: "Enterprise",
    DISCO.name: "Discovery",
}


class CharacterLines:
    def __init__(self, path: Path) -> None:
        self.path = path
        self.line_count = defaultdict(int)

    def collect(self) -> None:
        for episode in self.path.glob("*.htm*"):
            if EPISODE_REGEX.match(episode.name):
                for line in episode.read_text().split("\n"):
                    if m := LINE_REGEX.match(line):
                        self.line_count[m.group("name")] += 1

    @property
    def as_tablular_data(self) -> tuple[tuple[str, int, float], ...]:
        total = sum(self.line_count.values())
        r = []
        for k, v in self.line_count.items():
            percentage = round(v * 100 / total, 2)
            if percentage > 1:
                r.append((str(k), v, percentage))
        return tuple(reversed(sorted(r, key=lambda _: _[2])))

    def render(self) -> None:
        print(f"\n\n# {NAMES[self.path.name]}\n")
        print("| Name             | Total Lines | Percentage of Lines |")
        print("| ---------------- | :---------: | ------------------: |")
        for character, total, pct in self.as_tablular_data:
            print(f"| {character:16} | {total:11} | {pct:19} |")


if __name__ == "__main__":
    for series in (TOS, TNG, DS9, VOY, ENT, DISCO):
        counter = CharacterLines(series)
        counter.collect()
        counter.render()