This document specifies a set of Label Generation Rules (LGR) for the French language using a language-specific repertoire for the second level domain or domains identified above. The format of this file follows [RFC 7940]. This LGR is adapted from the “Reference LGR for the Second Level for the French Language” [Ref-LGR-fr-Latn], for details, see Change History below.
Standalone LGR: This LGR is designed to be used in a zone that does not cater to IDNs other than those valid under this LGR. This LGR lacks features that would allow its use in the context of another LGR in the same zone, and it may contain other features incompatible with such use.
Most references converge on 42 Latin code points.
There is no IDN table published in the IANA Repository of IDN Practices by a .fr ccTLD, but AFNIC has published specifications [700] listing the code points accepted for registration as IDNs in the .fr domain. PointQuébec has published a list of acceptable code points for the .quebec domain [701].
Letters documented in some references but not included:
U+00DF LATIN SMALL LETTER SHARP S
U+00E1 LATIN SMALL LETTER A WITH ACUTE
U+00E3 LATIN SMALL LETTER A WITH TILDE
U+00E4 LATIN SMALL LETTER A WITH DIAERESIS
U+00E5 LATIN SMALL LETTER A WITH RING ABOVE
U+00EC LATIN SMALL LETTER I WITH GRAVE
U+00ED LATIN SMALL LETTER I WITH ACUTE
U+00F2 LATIN SMALL LETTER O WITH GRAVE
U+00F3 LATIN SMALL LETTER O WITH ACUTE
U+00F5 LATIN SMALL LETTER O WITH TILDE
U+00F6 LATIN SMALL LETTER O WITH DIAERESIS
U+00F8 LATIN SMALL LETTER O WITH STROKE
U+00FA LATIN SMALL LETTER U WITH ACUTE
U+00FD LATIN SMALL LETTER Y WITH ACUTE
U+0101 LATIN SMALL LETTER A WITH MACRON
U+0113 LATIN SMALL LETTER E WITH MACRON
U+012B LATIN SMALL LETTER I WITH MACRON
U+01D4 LATIN SMALL LETTER U WITH CARON
A number of letters not considered essential to writing the core vocabulary of the language are nevertheless in common use. Where they have not been added to the core repertoire, they are flagged as “extended-cp” in the table of code points. A context rule is provided that by default will prohibit labels with such extended code points. To support extended single code points or code point sequences, delete the context “extended-cp” from their repertoire definition.
The sole “extended” code point in the May 18, 2021 version had been U+00F1 LATIN SMALL LETTER N WITH TILDE, cited by some references as being used in loan words. Based on additional research, it can also be found in personal names from the region of Brittany which argues for making it included by default.
It has been the practice of some second level registries to allow both the registration of an accented label as well as the pure ASCII fallback to the same entity, while disallowing the registration of the two labels to unrelated entities (See [CIRA]).
By default, this LGR treats all accented forms as optionally-enabled variants of the non-accented form of a label which would prevent them from being delegated to two different entities simultaneously. In order to restrict the number of allocatable variants, only one accented form can be allocated alongside the non-accented form. If the desired accented form has been applied for, the non-accented form would then be a variant that is allocatable to the original applicant. This covers the most common scenario of a single “correct” accented form, plus a non-accented “fallback”.
This extension to in-language variants is not compatible with using this LGR in a zone with another LGR and using the Common LGR to process conflicts between labels from multiple LGRs as described in Section 3 “Use of Multiple Reference LGRs in the Same Zone” in [Level-2-Overview].
No other variants are applicable when using the LGR in a standalone fashion.
Variants Limited to Standalone Use This LGR is not intended for use with LGRs for other languages or scripts in the same zone. The LGR does not define any “blocked” variants with code points in other languages or script that would prevent malicious registration of duplicate labels perceived as the same by users. As a result of transitivity, the scheme of internal variants defined here would have to be imposed on other LGRs that contain copies or variants of the affected code points.
If it is desired to support multiple languages in the same zone, the preferred method would be to support the corresponding script LGRs, which cater to the use of multiple languages, and are designed with the possibility of concurrent use in mind.
Certain variants in this LGR are defined as optionally enabled. They are using the context rule “enabled”. This context rule matches any label (it always succeeds). Any variant marked with when=“enabled” (in the XML file) is in force, while marking it with not-when=“enabled” causes the variant definition to be ignored in processing. This allows these variants to be disabled, for example, to better match legacy practice for a given zone.
Care must be taken to enable or disable variants so that all variant mappings to and from the same code point are either enabled or disabled at the same time, ensuring that all enabled variant mappings remain symmetric and transitive.
The specification of variants in this LGR follows the guidelines in [RFC 8228].
This LGR does not define named character classes.
The LGR includes the rules and actions to implement the following restrictions, some of which are mandated by the IDNA protocol. They are marked with ⍟ and included here by default. A special context rule enables optional variants by default.
when="enabled" in the xml will be active, while any with not-when="enabled" will be inactive.This LGR includes the default actions for LGRs as well as the action needed to invalidate labels with misplaced combining marks. They are marked with ⍟. For a description see [RFC 7940].
Because this LGR defines allocatable fallback variants the following default actions are applicable.
These actions resolve as “allocatable” any label where all variants are of type “fallback”, and as “valid” any label where all variants are of type “r-original”. Labels with a mix of variant types are resolved as “blocked”.
To account for original code points in a permuted variant, reflexive variant mappings with an “r-” prefix are used. (See [RFC 7940]). In particular, the mapping type “r-original” is given to any code point that has a fallback mapping, but that appears in its non-fallback form in the original label, and thus “maps to itself”.
Default actions that are triggered by the LGR-specific variant types described above limit the “allocatable” variant labels to those variants resulting from removal of the accents, while disallowing mixed use of variants with or without accents, except as in the original applied-for label. The use of such variants is "optionally_enabled_variants">optionally enabled in this LGR.
Note that the mapping types for variants are not symmetric: they depend on which code point is considered the source or the target in a given mapping. As specified in [RFC 7940], when mapping types are evaluated code points in a label that are unchanged use the type of their “reflexive” mapping. Per [RFC 7940] the actions are always applied one after the other, and the evaluation stops at the first action that assigns a disposition to a given label.
The LGR in this document has been adapted from the corresponding Reference LGR for the Second Level. The Second Level Reference LGR for the French Language was developed by Michel Suignard and Asmus Freytag, including input by Michael Everson, Nicholas Ostler, and Wil Tan, and based on multiple open public consultations.
Language tag has been updated.
Unicode Version has been updated.
Based on research showing use of ‘ñ’ in Breton names, U+00F1 LATIN SMALL LETTER N WITH TILDE has been changed from “extended-cp” to included by default.
Based on community comments expressed during the review of the Latin script Root Zone LGR, the need was established for fallback variants between French letters with diacritics and their ASCII base letters. These variants are enabled here by default, but are marked as “enabled” to allow registries to deactivate them if required.
This version modifies the Second Level Reference LGR for the French Language [Ref-LGR-fr-Latn] by injecting the complete (maximal) set of cross-repertoire variants, including any imposed by transitivity. Injected variants are marked by special comments. Any character classes, context and WLE rules required for testing are also imported. In all other respects, description or annotations have not been updated to reflect the injected variants. Any LGR elements that might pose a possible conflict when the LGR is used with the Common LGR for cross-repertoire variant resolution are clearly marked. All modifications are carried out mechanically; there may be an occasional context rule or similar that is injected because its definition relates to some repertoire element even though it can never be triggered by any label valid under the modified LGR.
General references for the language:
Atkins, Beryl T. et al. 1987. Robert · Collins dictionnaire français-anglais anglais-français = Collins · Robert French-English English-French dictionary. Paris: Dictionnaires le Robert. ISBN 2-85036-088-0. Glasgow: HarperCollins. ISBN 0-00-433451-5
Wikipedia: “French orthography”, https://en.wikipedia.org/wiki/French_alphabet
Omniglot: French (français) https://www.omniglot.com/writing/french.htm
In addition, the following references were consulted:
In the listing of the repertoire by code point, references starting from [0] refer to the version of the Unicode Standard in which the corresponding code point was initially encoded. Other references (starting from [100]) document usage of code points. Entries in the table may have multiple source reference values. In the listing of whole label evaluation and context rules, reference [150] indicates the source for common rules. For more details, see the Table of References below.
]]>