Fix case handling for various capitalization issues

[vikivivi]

• Fix multi words capitalization, camelCase, proper nouns, abbreviation
• Do not change suggested words in dictionary to lower case during build_dict()
• Capitalization decision is decided in fix_case()

Below is my basic simple test.sh and my dictionary_test.txt

$ cat dictionary_test.txt 
asscii->ASCII
austrailia->Australia
Micosoft->Microsoft
pinapple->pineapple
uspported->supported, unsupported,
skipt->skip, Skype, skipped,
lesstiff->LessTif
mangodb->MongoDB
ebya->eBay
mariadb->MariaDB
mysql->MySQL, mysql,

$ cat test.sh
#!/bin/sh

TEST_FILE="/tmp/test-input.txt"
rm -f "${TEST_FILE}"

# Test abbreviation, acronym, initialism: Suggested word coded as
#      upper case in dictionary.
test_abbreviation_01() {
    echo "asscii" >> "${TEST_FILE}"
    echo "Asscii" >> "${TEST_FILE}"
    echo "AssCii" >> "${TEST_FILE}"
    echo "ASSCII" >> "${TEST_FILE}"
}

# Test proper nouns: Misspelled coded as lower case in dictionary.
test_proper_nouns_lower_01() {
    echo "austrailia" >> "${TEST_FILE}"
    echo "Austrailia" >> "${TEST_FILE}"
    echo "AustRailia" >> "${TEST_FILE}"
    echo "AUSTRAILIA" >> "${TEST_FILE}"
}

# Test proper nouns, brand names: Misspelled coded as capitalize
#      in dictionary.
test_proper_nouns_capitalize_01() {
    echo "micosoft" >> "${TEST_FILE}"
    echo "Micosoft" >> "${TEST_FILE}"
    echo "MicoSoft" >> "${TEST_FILE}"
    echo "MICOSOFT" >> "${TEST_FILE}"
}

# Test typical single: Both misspelled and suggested word both coded
#      as lower case in dictionary.
test_typical_single_01() {
    echo "pinapple" >> "${TEST_FILE}"
    echo "Pinapple" >> "${TEST_FILE}"
}

# Test typical multiple: Both misspelled and multiple suggested words
#      both coded as lower case in dictionary.
test_typical_multiple_01() {
    echo "uspported" >> "${TEST_FILE}"
    echo "Uspported" >> "${TEST_FILE}"
    echo "USPPORTED" >> "${TEST_FILE}"
}

# Test typical multiple & mix: Misspelled coded in lower. Multiple
#      suggested words coded as lower & capitalize case in dictionary.
test_typical_multiple_mix_01() {
    echo "skipt" >> "${TEST_FILE}"
    echo "Skipt" >> "${TEST_FILE}"
    echo "SKIPT" >> "${TEST_FILE}"
}

# Test CamelCase basic: Suggested word coded as CamelCase in dictionary.
test_camelCase_01() {
    echo "lesstiff" >> "${TEST_FILE}"
    echo "lessTiff" >> "${TEST_FILE}"
    echo "Lesstiff" >> "${TEST_FILE}"
    echo "LessTiff" >> "${TEST_FILE}"
    echo "LESSTIFF" >> "${TEST_FILE}"
}

# Test CamelCase brand names: Suggested word coded as CamelCase
#      in dictionary.
test_camelCase_02() {
    echo "mangodb" >> "${TEST_FILE}"
    echo "mangoDb" >> "${TEST_FILE}"
    echo "mangoDB" >> "${TEST_FILE}"
    echo "Mangodb" >> "${TEST_FILE}"
    echo "MangoDb" >> "${TEST_FILE}"
    echo "MangoDB" >> "${TEST_FILE}"
}

# Test CamelCase brand names: Suggested word coded as CamelCase
#      in dictionary.
test_camelCase_03() {
    echo "ebya" >> "${TEST_FILE}"
    echo "eBya" >> "${TEST_FILE}"
    echo "Ebya" >> "${TEST_FILE}"
    echo "EBya" >> "${TEST_FILE}"
    echo "EBYA" >> "${TEST_FILE}"
}

# Special Test CamelCase, brand names: Misspelled is correct spelling
#      but incorrect case. Suggested word is coded as CamelCase in
#      dictionary. For custom dictionary only.
test_valid_word_camelCase_01() {
    echo "mariadb" >> "${TEST_FILE}"
    echo "mariaDb" >> "${TEST_FILE}"
    echo "mariaDB" >> "${TEST_FILE}"
    echo "Mariadb" >> "${TEST_FILE}"
    echo "MariaDb" >> "${TEST_FILE}"
    echo "MariaDB" >> "${TEST_FILE}"
}

# Special Test CamelCase, brand names: Misspelled is correct spelling
#      but incorrect case. Multiple suggested words are coded as CamelCase
#      and lower case in dictionary. For custom dictionary only.
test_valid_word_camelCase_02() {
    echo "mysql" >> "${TEST_FILE}"
    echo "mySql" >> "${TEST_FILE}"
    echo "mySQL" >> "${TEST_FILE}"
    echo "Mysql" >> "${TEST_FILE}"
    echo "MySql" >> "${TEST_FILE}"
    echo "MySQL" >> "${TEST_FILE}"
}

run_codespell() {
    codespell -D dictionary_test.txt "${TEST_FILE}"
    echo ""
    codespell -D dictionary_test.txt -w "${TEST_FILE}"
}


test_abbreviation_01
test_proper_nouns_lower_01
test_proper_nouns_capitalize_01
test_typical_single_01
test_typical_multiple_01
test_typical_multiple_mix_01
test_camelCase_01
test_camelCase_02
test_camelCase_03
test_valid_word_camelCase_01
test_valid_word_camelCase_02

run_codespell

[luzpaz]

@peternewman please review at your convenience

[peternewman]

I've finally merged #2223 which resolves some related issues, so can you merge that in @vikivivi ?

It's also got some test infrastructure we can make use of and extend!

[vikivivi]

@peternewman I have Git rebase my PR branch and generalise #2223 test infrastructure for various case handling checks. The test case from #2223 is re-adapted to this generalised function. All my test cases are added as well.

[shearer12345]

I'd be interested in the capabilities that this MR brings in - as I'd like to be able to check/correct capitalization (e.g. python->Python) . Is there anything I could do to support?