/inflect

Correctly generate plurals, ordinals, indefinite articles; convert numbers to words

Primary LanguagePythonMIT LicenseMIT

tests Ruff Code style: Black https://readthedocs.org/projects/inflect/badge/?version=latest https://img.shields.io/badge/skeleton-2023-informational https://tidelift.com/badges/package/pypi/inflect

NAME

inflect.py - Correctly generate plurals, singular nouns, ordinals, indefinite articles; convert numbers to words.

SYNOPSIS

import inflect

p = inflect.engine()

# METHODS:

# plural plural_noun plural_verb plural_adj singular_noun no num
# compare compare_nouns compare_nouns compare_adjs
# a an
# present_participle
# ordinal number_to_words
# join
# inflect classical gender
# defnoun defverb defadj defa defan


# UNCONDITIONALLY FORM THE PLURAL

print("The plural of ", word, " is ", p.plural(word))


# CONDITIONALLY FORM THE PLURAL

print("I saw", cat_count, p.plural("cat", cat_count))


# FORM PLURALS FOR SPECIFIC PARTS OF SPEECH

print(
    p.plural_noun("I", N1),
    p.plural_verb("saw", N1),
    p.plural_adj("my", N2),
    p.plural_noun("saw", N2),
)


# FORM THE SINGULAR OF PLURAL NOUNS

print("The singular of ", word, " is ", p.singular_noun(word))

# SELECT THE GENDER OF SINGULAR PRONOUNS

print(p.singular_noun("they"))  # 'it'
p.gender("feminine")
print(p.singular_noun("they"))  # 'she'


# DEAL WITH "0/1/N" -> "no/1/N" TRANSLATION:

print("There ", p.plural_verb("was", errors), p.no(" error", errors))


# USE DEFAULT COUNTS:

print(
    p.num(N1, ""),
    p.plural("I"),
    p.plural_verb(" saw"),
    p.num(N2),
    p.plural_noun(" saw"),
)
print("There ", p.num(errors, ""), p.plural_verb("was"), p.no(" error"))


# COMPARE TWO WORDS "NUMBER-INSENSITIVELY":

if p.compare(word1, word2):
    print("same")
if p.compare_nouns(word1, word2):
    print("same noun")
if p.compare_verbs(word1, word2):
    print("same verb")
if p.compare_adjs(word1, word2):
    print("same adj.")


# ADD CORRECT "a" OR "an" FOR A GIVEN WORD:

print("Did you want ", p.a(thing), " or ", p.an(idea))


# CONVERT NUMERALS INTO ORDINALS (i.e. 1->1st, 2->2nd, 3->3rd, etc.)

print("It was", p.ordinal(position), " from the left\n")

# CONVERT NUMERALS TO WORDS (i.e. 1->"one", 101->"one hundred and one", etc.)
# RETURNS A SINGLE STRING...

words = p.number_to_words(1234)
# "one thousand, two hundred and thirty-four"
words = p.number_to_words(p.ordinal(1234))
# "one thousand, two hundred and thirty-fourth"


# GET BACK A LIST OF STRINGS, ONE FOR EACH "CHUNK"...

words = p.number_to_words(1234, wantlist=True)
# ("one thousand","two hundred and thirty-four")


# OPTIONAL PARAMETERS CHANGE TRANSLATION:

words = p.number_to_words(12345, group=1)
# "one, two, three, four, five"

words = p.number_to_words(12345, group=2)
# "twelve, thirty-four, five"

words = p.number_to_words(12345, group=3)
# "one twenty-three, forty-five"

words = p.number_to_words(1234, andword="")
# "one thousand, two hundred thirty-four"

words = p.number_to_words(1234, andword=", plus")
# "one thousand, two hundred, plus thirty-four"
# TODO: I get no comma before plus: check perl

words = p.number_to_words(555_1202, group=1, zero="oh")
# "five, five, five, one, two, oh, two"

words = p.number_to_words(555_1202, group=1, one="unity")
# "five, five, five, unity, two, oh, two"

words = p.number_to_words(123.456, group=1, decimal="mark")
# "one two three mark four five six"
# TODO: DOCBUG: perl gives commas here as do I

# LITERAL STYLE ONLY NAMES NUMBERS LESS THAN A CERTAIN THRESHOLD...

words = p.number_to_words(9, threshold=10)  # "nine"
words = p.number_to_words(10, threshold=10)  # "ten"
words = p.number_to_words(11, threshold=10)  # "11"
words = p.number_to_words(1000, threshold=10)  # "1,000"

# JOIN WORDS INTO A LIST:

mylist = p.join(("apple", "banana", "carrot"))
# "apple, banana, and carrot"

mylist = p.join(("apple", "banana"))
# "apple and banana"

mylist = p.join(("apple", "banana", "carrot"), final_sep="")
# "apple, banana and carrot"


# REQUIRE "CLASSICAL" PLURALS (EG: "focus"->"foci", "cherub"->"cherubim")

p.classical()  # USE ALL CLASSICAL PLURALS

p.classical(all=True)  # USE ALL CLASSICAL PLURALS
p.classical(all=False)  # SWITCH OFF CLASSICAL MODE

p.classical(zero=True)  #  "no error" INSTEAD OF "no errors"
p.classical(zero=False)  #  "no errors" INSTEAD OF "no error"

p.classical(herd=True)  #  "2 buffalo" INSTEAD OF "2 buffalos"
p.classical(herd=False)  #  "2 buffalos" INSTEAD OF "2 buffalo"

p.classical(persons=True)  # "2 chairpersons" INSTEAD OF "2 chairpeople"
p.classical(persons=False)  # "2 chairpeople" INSTEAD OF "2 chairpersons"

p.classical(ancient=True)  # "2 formulae" INSTEAD OF "2 formulas"
p.classical(ancient=False)  # "2 formulas" INSTEAD OF "2 formulae"


# INTERPOLATE "plural()", "plural_noun()", "plural_verb()", "plural_adj()", "singular_noun()",
# a()", "an()", "num()" AND "ordinal()" WITHIN STRINGS:

print(p.inflect("The plural of {0} is plural('{0}')".format(word)))
print(p.inflect("The singular of {0} is singular_noun('{0}')".format(word)))
print(p.inflect("I saw {0} plural('cat',{0})".format(cat_count)))
print(
    p.inflect(
        "plural('I',{0}) "
        "plural_verb('saw',{0}) "
        "plural('a',{1}) "
        "plural_noun('saw',{1})".format(N1, N2)
    )
)
print(
    p.inflect(
        "num({0}, False)plural('I') "
        "plural_verb('saw') "
        "num({1}, False)plural('a') "
        "plural_noun('saw')".format(N1, N2)
    )
)
print(p.inflect("I saw num({0}) plural('cat')\nnum()".format(cat_count)))
print(p.inflect("There plural_verb('was',{0}) no('error',{0})".format(errors)))
print(p.inflect("There num({0}, False)plural_verb('was') no('error')".format(errors)))
print(p.inflect("Did you want a('{0}') or an('{1}')".format(thing, idea)))
print(p.inflect("It was ordinal('{0}') from the left".format(position)))


# ADD USER-DEFINED INFLECTIONS (OVERRIDING INBUILT RULES):

p.defnoun("VAX", "VAXen")  # SINGULAR => PLURAL

p.defverb(
    "will",  # 1ST PERSON SINGULAR
    "shall",  # 1ST PERSON PLURAL
    "will",  # 2ND PERSON SINGULAR
    "will",  # 2ND PERSON PLURAL
    "will",  # 3RD PERSON SINGULAR
    "will",  # 3RD PERSON PLURAL
)

p.defadj("hir", "their")  # SINGULAR => PLURAL

p.defa("h")  # "AY HALWAYS SEZ 'HAITCH'!"

p.defan("horrendous.*")  # "AN HORRENDOUS AFFECTATION"

DESCRIPTION

The methods of the class engine in module inflect.py provide plural inflections, singular noun inflections, "a"/"an" selection for English words, and manipulation of numbers as words.

Plural forms of all nouns, most verbs, and some adjectives are provided. Where appropriate, "classical" variants (for example: "brother" -> "brethren", "dogma" -> "dogmata", etc.) are also provided.

Single forms of nouns are also provided. The gender of singular pronouns can be chosen (for example "they" -> "it" or "she" or "he" or "they").

Pronunciation-based "a"/"an" selection is provided for all English words, and most initialisms.

It is also possible to inflect numerals (1,2,3) to ordinals (1st, 2nd, 3rd) and to English words ("one", "two", "three").

In generating these inflections, inflect.py follows the Oxford English Dictionary and the guidelines in Fowler's Modern English Usage, preferring the former where the two disagree.

The module is built around standard British spelling, but is designed to cope with common American variants as well. Slang, jargon, and other English dialects are not explicitly catered for.

Where two or more inflected forms exist for a single word (typically a "classical" form and a "modern" form), inflect.py prefers the more common form (typically the "modern" one), unless "classical" processing has been specified (see MODERN VS CLASSICAL INFLECTIONS).

FORMING PLURALS AND SINGULARS

Inflecting Plurals and Singulars

All of the plural... plural inflection methods take the word to be inflected as their first argument and return the corresponding inflection. Note that all such methods expect the singular form of the word. The results of passing a plural form are undefined (and unlikely to be correct). Similarly, the si... singular inflection method expects the plural form of the word.

The plural... methods also take an optional second argument, which indicates the grammatical "number" of the word (or of another word with which the word being inflected must agree). If the "number" argument is supplied and is not 1 (or "one" or "a", or some other adjective that implies the singular), the plural form of the word is returned. If the "number" argument does indicate singularity, the (uninflected) word itself is returned. If the number argument is omitted, the plural form is returned unconditionally.

The si... method takes a second argument in a similar fashion. If it is some form of the number 1, or is omitted, the singular form is returned. Otherwise the plural is returned unaltered.

The various methods of inflect.engine are:

plural_noun(word, count=None)

The method plural_noun() takes a singular English noun or pronoun and returns its plural. Pronouns in the nominative ("I" -> "we") and accusative ("me" -> "us") cases are handled, as are possessive pronouns ("mine" -> "ours").

plural_verb(word, count=None)

The method plural_verb() takes the singular form of a conjugated verb (that is, one which is already in the correct "person" and "mood") and returns the corresponding plural conjugation.

plural_adj(word, count=None)

The method plural_adj() takes the singular form of certain types of adjectives and returns the corresponding plural form. Adjectives that are correctly handled include: "numerical" adjectives ("a" -> "some"), demonstrative adjectives ("this" -> "these", "that" -> "those"), and possessives ("my" -> "our", "cat's" -> "cats'", "child's" -> "childrens'", etc.)

plural(word, count=None)

The method plural() takes a singular English noun, pronoun, verb, or adjective and returns its plural form. Where a word has more than one inflection depending on its part of speech (for example, the noun "thought" inflects to "thoughts", the verb "thought" to "thought"), the (singular) noun sense is preferred to the (singular) verb sense.

Hence plural("knife") will return "knives" ("knife" having been treated as a singular noun), whereas plural("knifes") will return "knife" ("knifes" having been treated as a 3rd person singular verb).

The inherent ambiguity of such cases suggests that, where the part of speech is known, plural_noun, plural_verb, and plural_adj should be used in preference to plural.

singular_noun(word, count=None)

The method singular_noun() takes a plural English noun or pronoun and returns its singular. Pronouns in the nominative ("we" -> "I") and accusative ("us" -> "me") cases are handled, as are possessive pronouns ("ours" -> "mine"). When third person singular pronouns are returned they take the neuter gender by default ("they" -> "it"), not ("they"-> "she") nor ("they" -> "he"). This can be changed with gender().

Note that all these methods ignore any whitespace surrounding the word being inflected, but preserve that whitespace when the result is returned. For example, plural(" cat ") returns " cats ".

gender(genderletter)

The third person plural pronoun takes the same form for the female, male and neuter (e.g. "they"). The singular however, depends upon gender (e.g. "she", "he", "it" and "they" -- "they" being the gender neutral form.) By default singular_noun returns the neuter form, however, the gender can be selected with the gender method. Pass the first letter of the gender to gender to return the f(eminine), m(asculine), n(euter) or t(hey) form of the singular. e.g. gender('f') followed by singular_noun('themselves') returns 'herself'.

Numbered plurals

The plural... methods return only the inflected word, not the count that was used to inflect it. Thus, in order to produce "I saw 3 ducks", it is necessary to use:

print("I saw", N, p.plural_noun(animal, N))

Since the usual purpose of producing a plural is to make it agree with a preceding count, inflect.py provides a method (no(word, count)) which, given a word and a(n optional) count, returns the count followed by the correctly inflected word. Hence the previous example can be rewritten:

print("I saw ", p.no(animal, N))

In addition, if the count is zero (or some other term which implies zero, such as "zero", "nil", etc.) the count is replaced by the word "no". Hence, if N had the value zero, the previous example would print (the somewhat more elegant):

I saw no animals

rather than:

I saw 0 animals

Note that the name of the method is a pun: the method returns either a number (a No.) or a "no", in front of the inflected word.

Reducing the number of counts required

In some contexts, the need to supply an explicit count to the various plural... methods makes for tiresome repetition. For example:

print(
    plural_adj("This", errors),
    plural_noun(" error", errors),
    plural_verb(" was", errors),
    " fatal.",
)

inflect.py therefore provides a method (num(count=None, show=None)) which may be used to set a persistent "default number" value. If such a value is set, it is subsequently used whenever an optional second "number" argument is omitted. The default value thus set can subsequently be removed by calling num() with no arguments. Hence we could rewrite the previous example:

p.num(errors)
print(p.plural_adj("This"), p.plural_noun(" error"), p.plural_verb(" was"), "fatal.")
p.num()

Normally, num() returns its first argument, so that it may also be "inlined" in contexts like:

print(p.num(errors), p.plural_noun(" error"), p.plural_verb(" was"), " detected.")
if severity > 1:
    print(
        p.plural_adj("This"), p.plural_noun(" error"), p.plural_verb(" was"), "fatal."
    )

However, in certain contexts (see INTERPOLATING INFLECTIONS IN STRINGS) it is preferable that num() return an empty string. Hence num() provides an optional second argument. If that argument is supplied (that is, if it is defined) and evaluates to false, num returns an empty string instead of its first argument. For example:

print(p.num(errors, 0), p.no("error"), p.plural_verb(" was"), " detected.")
if severity > 1:
    print(
        p.plural_adj("This"), p.plural_noun(" error"), p.plural_verb(" was"), "fatal."
    )

Number-insensitive equality

inflect.py also provides a solution to the problem of comparing words of differing plurality through the methods compare(word1, word2), compare_nouns(word1, word2), compare_verbs(word1, word2), and compare_adjs(word1, word2). Each of these methods takes two strings, and compares them using the corresponding plural-inflection method (plural(), plural_noun(), plural_verb(), and plural_adj() respectively).

The comparison returns true if:

  • the strings are equal, or
  • one string is equal to a plural form of the other, or
  • the strings are two different plural forms of the one word.

Hence all of the following return true:

p.compare("index", "index")  # RETURNS "eq"
p.compare("index", "indexes")  # RETURNS "s:p"
p.compare("index", "indices")  # RETURNS "s:p"
p.compare("indexes", "index")  # RETURNS "p:s"
p.compare("indices", "index")  # RETURNS "p:s"
p.compare("indices", "indexes")  # RETURNS "p:p"
p.compare("indexes", "indices")  # RETURNS "p:p"
p.compare("indices", "indices")  # RETURNS "eq"

As indicated by the comments in the previous example, the actual value returned by the various compare methods encodes which of the three equality rules succeeded: "eq" is returned if the strings were identical, "s:p" if the strings were singular and plural respectively, "p:s" for plural and singular, and "p:p" for two distinct plurals. Inequality is indicated by returning an empty string.

It should be noted that two distinct singular words which happen to take the same plural form are not considered equal, nor are cases where one (singular) word's plural is the other (plural) word's singular. Hence all of the following return false:

p.compare("base", "basis")  # ALTHOUGH BOTH -> "bases"
p.compare("syrinx", "syringe")  # ALTHOUGH BOTH -> "syringes"
p.compare("she", "he")  # ALTHOUGH BOTH -> "they"

p.compare("opus", "operas")  # ALTHOUGH "opus" -> "opera" -> "operas"
p.compare("taxi", "taxes")  # ALTHOUGH "taxi" -> "taxis" -> "taxes"

Note too that, although the comparison is "number-insensitive" it is not case-insensitive (that is, plural("time","Times") returns false. To obtain both number and case insensitivity, use the lower() method on both strings (that is, plural("time".lower(), "Times".lower()) returns true).

Related Functionality

Shout out to these libraries that provide related functionality:

  • WordSet parses identifiers like variable names into sets of words suitable for re-assembling in another form.
  • word2number converts words to a number.

For Enterprise

Available as part of the Tidelift Subscription.

This project and the maintainers of thousands of other packages are working with Tidelift to deliver one enterprise subscription that covers all of the open source you use.

Learn more.

Security Contact

To report a security vulnerability, please use the Tidelift security contact. Tidelift will coordinate the fix and disclosure.