Spaces:
Sleeping
Sleeping
| import streamlit as st | |
| import langcodes | |
| # https://huggingface.co/blog/streamlit-spaces | |
| langtext = st.text_input("language lookup using https://github.com/rspeer/langcodes, see also https://r12a.github.io/app-subtags/", "english") | |
| st.write("Checking whether the tag is valid. That is, the language, script, territory, and variants (if present) are all tags that have meanings assigned by IANA.") | |
| if langcodes.tag_is_valid(langtext): | |
| st.write(f"...True! '{langtext}' parses meaningfully as a language tag according to IANA.") | |
| else: | |
| st.write(f"...False! '{langtext}' doesn't parse meaningfully as a language tag according to IANA, some of its subcomponents may be invalid or it might be a natural language description.") | |
| try: | |
| lang = langcodes.Language.get(langtext) | |
| # st.write(f"{lang} is the BCP-47 tag.") | |
| if "unknown" in lang.display_name().lower(): | |
| st.write(f"Attempting to lookup the code directly gives us '{lang.display_name()}', attempting to search for it as a natural language string.") | |
| lang = None | |
| except langcodes.LanguageTagError as e: | |
| st.write(f"Could not lookup code directly, attempting to search for it as a natural language string.") | |
| lang = None | |
| if lang is None: | |
| try: | |
| found = langcodes.find(langtext) | |
| lang = found | |
| st.write(f"natural language search found the following BCP-47 tag: {lang}") | |
| except LookupError as e: | |
| st.write(f"Unable to look up language code.") | |
| lang = None | |
| #st.write(f"langcodes found the following tag: {type(found)}") # a Language object | |
| if lang is not None: | |
| display = lang.display_name() | |
| st.write(f"Best-match BCP-47 tag for '{langtext}', according to the langcodes library: {lang}") | |
| st.write(f"Breakdown of tag components: {lang.describe()}") | |
| st.write(f"Display name for {lang}: {lang.display_name()}") | |
| st.write(f"Autonym for {lang}: {lang.autonym()}") | |
| b_variant = lang.to_alpha3(variant='B') | |
| t_variant = lang.to_alpha3(variant='T') | |
| st.write(f"ISO 639-3 'alpha3' code, 'terminology' variant (deprecated): {t_variant}") | |
| st.write(f"ISO 639-3 'alpha3' code, 'bibliographic' variant (deprecated): {b_variant}") | |
| broader_tags = lang.broader_tags() | |
| st.write(f"Broader tags for this language, if any: {broader_tags}") | |
| st.write(f"Correct, standardized, BCP-47 tag for {langtext}, according to the langcodes library: {langcodes.standardize_tag(lang)}") | |