initial commit

app.py

@@ -0,0 +1,110 @@
+from datetime import datetime
+
+import datacards
+
+from datacards import (
+    considerations_page,
+    considerations_summary,
+    context_page,
+    context_summary,
+    curation_page,
+    curation_summary,
+    gem_page,
+    gem_summary,
+    overview_page,
+    overview_summary,
+    results_page,
+    results_summary,
+)
+
+import streamlit as st
+
+##################
+## streamlit
+##################
+st.set_page_config(
+    page_title="GEM Data Card Input Form",
+    page_icon="https://avatars.githubusercontent.com/u/72612128",
+    layout="wide",
+    initial_sidebar_state="auto",
+)
+
+page_description = """
+# GEM Data Card Input Form
+
+This application was designed to support the GEM v2 data hackathon.
+
+It allows users to fill out all of the information going into the data documentation when submitting a new dataset.
+
+Use the left sidebar to navigate:
+- "**Dataset at a Glance**" shows selected information and tracks progress
+- Each of the "**Section:**" pages opens a form for a specific section of the card
+- Go to "**Review and Save**" when you are done to save your data card
+"""
+
+_N_FIELDS = datacards.considerations.N_FIELDS + \
+    datacards.context.N_FIELDS + \
+    datacards.curation.N_FIELDS + \
+    datacards.gem.N_FIELDS + \
+    datacards.overview.N_FIELDS + \
+    datacards.results.N_FIELDS
+
+def main():
+    if "save_state" not in st.session_state:
+        st.session_state.save_state = {}
+
+    if "card_dict" not in st.session_state:
+        st.session_state.card_dict = {}
+
+    st.sidebar.markdown(page_description, unsafe_allow_html=True)
+    pages = {
+        "Dataset at a Glance": glance_page,
+        "Section: Dataset Overview": overview_page,
+        "Section: Dataset in GEM": gem_page,
+        "Section: Dataset Curation": curation_page,
+        "Section: Previous Results": results_page,
+        "Section: Considerations for Using Data": considerations_page,
+        "Section: Broader Social Context": context_page,
+        "Review and Save": review_page,
+    }
+    app_mode = st.sidebar.radio(
+        label="Navigation menu:",
+        options=list(pages.keys()),
+        index=0,
+    )
+    st.markdown("#### GEM Data Card Input Form")
+    pages[app_mode]()
+
+def glance_page():
+    with st.expander("Dataset at a Glance", expanded=True):
+        st.markdown(f"### Dataset Name: {st.session_state.save_state.get('dataset_name', '')}")
+        dataset_summary = ""
+        dataset_summary += f"- **Dataset Website**: {st.session_state.save_state.get('overview_where_website', '')}\n"
+        dataset_summary += f"- **Dataset Contact**: {st.session_state.save_state.get('overview_where_contact-name', '')}\n"
+        dataset_summary += f"- **Dataset License**: {st.session_state.save_state.get('overview_languages_license', '')}\n"
+        dataset_summary += f"- **Multilingual Dataset**: {st.session_state.save_state.get('overview_languages_is-multilingual', '')}\n"
+        dataset_summary += f"- **Dataset Languages**: {', '.join(st.session_state.save_state.get('overview_languages_language-names', []))}\n"
+        dataset_summary += f"- **Dataset Supported Task**: {st.session_state.save_state.get('overview_languages_task', '')}\n"
+        dataset_summary += f"- **Communicative Goal**: {st.session_state.save_state.get('dataset_communicative', '')}\n"
+        dataset_summary += f"- **Language Data Origin**: {st.session_state.save_state.get('curation_language_origin', '')}\n"
+        dataset_summary += f"- **Annotation Data Origin**: {st.session_state.save_state.get('curation_annotation_origin', '')}\n"
+        dataset_summary += f"- **Likelihood of PII**: {st.session_state.save_state.get('pii_likelihood', '')}\n"
+        st.markdown(dataset_summary + "---\n")
+        num_fields = sum([len(dct) for k in st.session_state.get("card_dict", {}) for dct in st.session_state.card_dict.get(k, {}).values()])
+        st.markdown(f"You have currently filled out **{num_fields} of {_N_FIELDS} required fields** in the data card.")
+    left_col, right_col = st.columns(2)
+    with left_col:
+        overview_summary()
+        gem_summary()
+        curation_summary()
+    with right_col:
+        results_summary()
+        considerations_summary()
+        context_summary()
+
+def review_page():
+    st.write(st.session_state.get("card_dict", {}))
+    # TODO add buttons to save and download
+
+if __name__ == "__main__":
+    main()

datacards/__init__.py

@@ -0,0 +1,6 @@
+from .considerations import considerations_page, considerations_summary
+from .context import context_page, context_summary
+from .curation import curation_page, curation_summary
+from .gem import gem_page, gem_summary
+from .overview import overview_page, overview_summary
+from .results import results_page, results_summary

datacards/considerations.py

@@ -0,0 +1,13 @@
+import streamlit as st
+
+from .streamlit_utils import (
+    make_text_input
+)
+
+N_FIELDS = 1
+
+def considerations_page():
+    return None
+
+def considerations_summary():
+    return None

datacards/context.py

@@ -0,0 +1,13 @@
+import streamlit as st
+
+from .streamlit_utils import (
+    make_text_input
+)
+
+N_FIELDS = 1
+
+def context_page():
+    return None
+
+def context_summary():
+    return None

datacards/curation.py

@@ -0,0 +1,13 @@
+import streamlit as st
+
+from .streamlit_utils import (
+    make_text_input
+)
+
+N_FIELDS = 1
+
+def curation_page():
+    return None
+
+def curation_summary():
+    return None

datacards/gem.py

@@ -0,0 +1,13 @@
+import streamlit as st
+
+from .streamlit_utils import (
+    make_text_input
+)
+
+N_FIELDS = 1
+
+def gem_page():
+    return None
+
+def gem_summary():
+    return None

datacards/overview.py

@@ -0,0 +1,194 @@
+import json
+import streamlit as st
+
+from os.path import join as pjoin
+
+from .streamlit_utils import (
+    make_multiselect,
+    make_selectbox,
+    make_text_area,
+    make_text_input,
+    make_radio,
+)
+
+N_FIELDS_WHERE = 9
+N_FIELDS_LANGUAGES = 6
+N_FIELDS_CREDIT = 3
+N_FIELDS_STRUCTURE = 7
+
+N_FIELDS = N_FIELDS_WHERE + \
+    N_FIELDS_LANGUAGES + \
+    N_FIELDS_CREDIT + \
+    N_FIELDS_STRUCTURE
+
+
+languages_bcp47 = [
+    x
+    for x in json.load(open(pjoin("resources", "bcp47.json"), encoding="utf-8"))["subtags"]
+    if x["type"] == "language"
+]
+
+license_list = json.load(open(pjoin("resources", "licenses.json"), encoding="utf-8"))
+
+def overview_page():
+    st.session_state.card_dict["overview"] = st.session_state.card_dict.get("overview", {})
+    with st.expander("Where to find", expanded=False):
+        key_pref = ["overview", "where"]
+        st.session_state.card_dict["overview"]["where"] = st.session_state.card_dict.get("where", {})
+        make_text_input(
+            label="What is the webpage for the dataset (if it exists)?",
+            key_list=key_pref + ["website"],
+            help="[URL]",
+        )
+        make_text_input(
+            label="What is the link to where the original dataset is hosted?",
+            key_list=key_pref + ["data-url"],
+            help="[URL]",
+        )
+        make_text_input(
+            label="What is the link to the paper describing the dataset (open access preferred)?",
+            key_list=key_pref + ["paper-url"],
+            help="[URL]",
+        )
+        make_text_area(
+            label="Provide the BibTex-formatted reference for the dataset.",
+            key_list=key_pref + ["paper-bibtext"],
+            help="[free text]",
+        )
+        make_radio(
+            label="Does the dataset have an active leaderboard?",
+            options=["no", "yes"],
+            key_list=key_pref + ["has-leaderboard"],
+            help="If no, enter N/A for the following two fields",
+        )
+        make_text_input(
+            label="Provide a link to the leaderboard if it exists. Otherwise, enter N/A.",
+            key_list=key_pref + ["leaderboard-url"],
+            help="[URL] or N/A",
+        )
+        make_text_area(
+            label="Briefly describe how the leaderboard evaluates models if it exists. Otherwise, enter N/A.",
+            key_list=key_pref + ["leaderboard-description"],
+            help="[free text; a paragraph] or N/A",
+        )
+        make_text_input(
+            label="If known, provide the name of at least one person the reader can contact for questions about the dataset.",
+            key_list=key_pref + ["contact-name"],
+            help="[free text]",
+        )
+        make_text_input(
+            label="If known, provide the email of at least one person the reader can contact for questions about the dataset.",
+            key_list=key_pref + ["contact-email"],
+            help="[free text]",
+        )
+    with st.expander("Languages and Intended Use", expanded=False):
+        key_pref = ["overview", "languages"]
+        st.session_state.card_dict["overview"]["languages"] = st.session_state.card_dict.get("languages", {})
+        make_radio(
+            label="Is the dataset multilingual?",
+            options=["no", "yes"],
+            key_list=key_pref + ["is-multilingual"],
+            help="More than one language present in all of the text fields",
+        )
+        make_multiselect(
+            label="What languages/dialects are covered in the dataset?",
+            key_list=key_pref + ["language-names"],
+            options=[
+                ", ".join(x["description"]) for x in languages_bcp47
+            ],
+            help="This is a comprehensive list of languages obtained from the BCP-47 standard list.",
+        )
+        make_text_area(
+            label="What is the intended use of the dataset?",
+            key_list=key_pref + ["intended-use"],
+            help="[free text, paragraphs]",
+        )
+        make_selectbox(
+            label="What is the license of the dataset?",
+            key_list=key_pref + ["license"],
+            options=license_list,
+            help="select `other` if missing from list, `unkown` if not provided"
+        )
+        make_text_input(
+            label="What primary task does the dataset support?",
+            key_list=key_pref + ["task"],
+            help="[free text]",
+        )
+        make_text_area(
+            label="Provide a short description of the communicative goal of a model trained for this task on this dataset.",
+            key_list=key_pref + ["communicative"],
+            help="[free text, a paragraph] (e.g., describe a restaurant from a structured representation of its attributes)",
+        )
+    with st.expander("Credit", expanded=False):
+        key_pref = ["overview", "credit"]
+        st.session_state.card_dict["overview"]["credit"] = st.session_state.card_dict.get("credit", {})
+        make_text_input(
+            label="Who created the original dataset? List the people involved in collecting the dataset and their affiliation(s).",
+            key_list=key_pref + ["creators"],
+            help="name (affiliation); comma-separated",
+        )
+        make_text_input(
+            label="Who funded the data creation?",
+            key_list=key_pref + ["funding"],
+            help="[free text] enter N/A if unkown",
+        )
+        make_text_input(
+            label="Who contributed to the data card and adding the dataset to GEM? List the people+affiliations involved in creating this data card and who helped integrate this dataset into GEM.",
+            key_list=key_pref + ["gem-added-by"],
+            help="name (affiliation); comma-separated",
+        )
+    with st.expander("Structure", expanded=False):
+        key_pref = ["overview", "structure"]
+        st.session_state.card_dict["overview"]["structure"] = st.session_state.card_dict.get("structure", {})
+        data_fields_help = """
+        [free text; paragraphs]
+        - Mention their data type, and whether and how they are used as part of the generation pipeline.
+        - Describe each fields' attributes, such as whether they are at the character level or word level, whether they are contiguous or not, etc.
+        - If the datasets contain example IDs, state whether they have an inherent meaning, such as a mapping to other datasets or pointing to relationships between data points.
+        """
+        make_text_area(
+            label="List and describe the fields present in the dataset.",
+            key_list=key_pref + ["data-fields"],
+            help=data_fields_help,
+        )
+        make_text_area(
+            label="How was the dataset structure determined?",
+            key_list=key_pref + ["structure-description"],
+            help="[free text; paragraph]",
+        )
+        make_text_area(
+            label="How were the labels chosen?",
+            key_list=key_pref + ["structure-labels"],
+            help="[free text; paragraph]",
+        )
+        make_text_area(
+            label="Provide a JSON formatted example of a typical instance in the dataset.",
+            key_list=key_pref + ["structure-example"],
+            help="[JSON]",
+        )
+        make_text_area(
+            label="Describe and name the splits in the dataset if there are more than one.",
+            key_list=key_pref + ["structure-splits"],
+            help="[free text, paragraphs] - As appropriate, provide any descriptive statistics for the features, such as size, average lengths of input and output.",
+        )
+        make_text_area(
+            label="Describe any criteria for splitting the data, if used. If there are differences between the splits (e.g., if the training annotations are machine-generated and the dev and test ones are created by humans, or if different numbers of annotators contributed to each example), describe them here.",
+            key_list=key_pref + ["structure-splits-criteria"],
+            help="[free text, paragraphs]",
+        )
+        make_text_area(
+            label="What does an outlier of the dataset in terms of length/perplexity/embedding look like?",
+            key_list=key_pref + ["structure-outlier"],
+            help="[free text + json formatted text/file for an example]",
+        )
+
+
+def overview_summary():
+    with st.expander("Dataset Overview Completion", expanded=True):
+        completion_markdown = ""
+        completion_markdown += f"- **Overall competion:**\n  - {sum([len(dct) for dct in st.session_state.card_dict.get('overview', {}).values()])} of {N_FIELDS} fields\n"
+        completion_markdown += f"- **Sub-section - Where to find:**\n  - {len(st.session_state.card_dict.get('overview', {}).get('where', {}))} of {N_FIELDS_WHERE} fields\n"
+        completion_markdown += f"- **Sub-section - Languages and Intended Use:**\n  - {len(st.session_state.card_dict.get('overview', {}).get('languages', {}))} of {N_FIELDS_LANGUAGES} fields\n"
+        completion_markdown += f"- **Sub-section - Credit:**\n  - {len(st.session_state.card_dict.get('overview', {}).get('credit', {}))} of {N_FIELDS_CREDIT} fields\n"
+        completion_markdown += f"- **Sub-section - Structure:**\n  - {len(st.session_state.card_dict.get('overview', {}).get('structure', {}))} of {N_FIELDS_STRUCTURE} fields\n"
+        st.markdown(completion_markdown)

datacards/results.py

@@ -0,0 +1,13 @@
+import streamlit as st
+
+from .streamlit_utils import (
+    make_text_input
+)
+
+N_FIELDS = 1
+
+def results_page():
+    return None
+
+def results_summary():
+    return None

datacards/streamlit_utils.py

@@ -0,0 +1,120 @@
+import streamlit as st
+
+
+# Streamlit widgets with persistence
+# TODO: better detection of whether a field has been updated
+def update_card_dict(key_list, default=None):
+    state_key = "_".join(key_list)
+    if st.session_state.save_state.get(state_key, default) != default:
+        card_key = key_list[-1]
+        current_dict = st.session_state.card_dict
+        for key in key_list[:-1]:
+            current_dict = current_dict[key]
+        current_dict[card_key] = st.session_state.save_state[state_key]
+
+
+def make_multiselect(
+    key_list, label, options, format_func=lambda x: x, help="", default=None
+):
+    key = "_".join(key_list)
+    if key in st.session_state:
+        st.session_state.save_state[key] = st.session_state[key]
+    elif default is not None:
+        st.session_state.save_state[key] = default
+    res = st.multiselect(
+        label=label,
+        options=options,
+        format_func=format_func,
+        key=key,
+        default=st.session_state.save_state.get(key, []),
+        help=help,
+    )
+    update_card_dict(key_list, default=[])
+    return res
+
+
+def make_selectbox(key_list, label, options, format_func=lambda x: x, help="", index=None, on_change=None):
+    key = "_".join(key_list)
+    if key in st.session_state:
+        st.session_state.save_state[key] = st.session_state[key]
+    elif index is not None:
+        st.session_state.save_state[key] = options[index]
+    res = st.selectbox(
+        label=label,
+        options=options,
+        format_func=format_func,
+        key=key,
+        index=options.index(
+            st.session_state.save_state.get(key, options[0])
+        ),  # if st.session_state.save_state.get(key, options[0]) in options else 0,
+        help=help,
+        on_change=on_change,
+    )
+    update_card_dict(key_list, default=[])
+    return res
+
+
+def make_radio(key_list, label, options, format_func=lambda x: x, help="", index=None):
+    key = "_".join(key_list)
+    if key in st.session_state:
+        st.session_state.save_state[key] = st.session_state[key]
+    elif index is not None:
+        st.session_state.save_state[key] = options[index]
+    res = st.radio(
+        label=label,
+        options=options,
+        format_func=format_func,
+        key=key,
+        index=options.index(st.session_state.save_state.get(key, options[0])),
+        help=help,
+    )
+    update_card_dict(key_list)
+    return res
+
+
+def make_text_input(key_list, label, help="", value=None):
+    key = "_".join(key_list)
+    if key in st.session_state:
+        st.session_state.save_state[key] = st.session_state[key]
+    elif value is not None:
+        st.session_state.save_state[key] = value
+    res = st.text_input(
+        label=label,
+        key=key,
+        value=st.session_state.save_state.get(key, ""),
+        help=help,
+    )
+    update_card_dict(key_list, default="")
+    return res
+
+
+def make_text_area(key_list, label, help="", value=None):
+    key = "_".join(key_list)
+    if key in st.session_state:
+        st.session_state.save_state[key] = st.session_state[key]
+    elif value is not None:
+        st.session_state.save_state[key] = value
+    res =  st.text_area(
+        label=label,
+        key=key,
+        value=st.session_state.save_state.get(key, ""),
+        help=help,
+    )
+    update_card_dict(key_list, default="")
+    return res
+
+
+def make_checkbox(key_list, label, help="", value=None):
+    key = "_".join(key_list)
+    if key in st.session_state:
+        st.session_state.save_state[key] = st.session_state[key]
+    elif value is not None:
+        st.session_state.save_state[key] = value
+    res = st.checkbox(
+        label=label,
+        key=key,
+        value=st.session_state.save_state.get(key, False),
+        help=help,
+    )
+    update_card_dict(key_list)
+    return res

resources/licenses.json

@@ -0,0 +1,452 @@
+[
+    "other: Other license",
+    "unknown: License information unavailable",
+    "0bsd: BSD Zero Clause License",
+    "aal: Attribution Assurance License",
+    "abstyles: Abstyles License",
+    "adobe-2006: Adobe Systems Incorporated Source Code License Agreement",
+    "adobe-glyph: Adobe Glyph List License",
+    "adsl: Amazon Digital Services License",
+    "afl-1.1: Academic Free License v1.1",
+    "afl-1.2: Academic Free License v1.2",
+    "afl-2.0: Academic Free License v2.0",
+    "afl-2.1: Academic Free License v2.1",
+    "afl-3.0: Academic Free License v3.0",
+    "afmparse: Afmparse License",
+    "agpl-1.0: Affero General Public License v1.0",
+    "agpl-1.0-only: Affero General Public License v1.0 only",
+    "agpl-1.0-or-later: Affero General Public License v1.0 or later",
+    "agpl-3.0: GNU Affero General Public License v3.0",
+    "agpl-3.0-only: GNU Affero General Public License v3.0 only",
+    "agpl-3.0-or-later: GNU Affero General Public License v3.0 or later",
+    "aladdin: Aladdin Free Public License",
+    "amdplpa: AMD's plpa_map.c License",
+    "aml: Apple MIT License",
+    "ampas: Academy of Motion Picture Arts and Sciences BSD",
+    "antlr-pd: ANTLR Software Rights Notice",
+    "antlr-pd-fallback: ANTLR Software Rights Notice with license fallback",
+    "apache-1.0: Apache License 1.0",
+    "apache-1.1: Apache License 1.1",
+    "apache-2.0: Apache License 2.0",
+    "apafml: Adobe Postscript AFM License",
+    "apl-1.0: Adaptive Public License 1.0",
+    "apsl-1.0: Apple Public Source License 1.0",
+    "apsl-1.1: Apple Public Source License 1.1",
+    "apsl-1.2: Apple Public Source License 1.2",
+    "apsl-2.0: Apple Public Source License 2.0",
+    "artistic-1.0: Artistic License 1.0",
+    "artistic-1.0-cl8: Artistic License 1.0 w/clause 8",
+    "artistic-1.0-perl: Artistic License 1.0 (Perl)",
+    "artistic-2.0: Artistic License 2.0",
+    "bahyph: Bahyph License",
+    "barr: Barr License",
+    "beerware: Beerware License",
+    "bittorrent-1.0: BitTorrent Open Source License v1.0",
+    "bittorrent-1.1: BitTorrent Open Source License v1.1",
+    "blessing: SQLite Blessing",
+    "blueoak-1.0.0: Blue Oak Model License 1.0.0",
+    "borceux: Borceux license",
+    "bsd-1-clause: BSD 1-Clause License",
+    "bsd-2-clause: BSD 2-Clause \"Simplified\" License",
+    "bsd-2-clause-freebsd: BSD 2-Clause FreeBSD License",
+    "bsd-2-clause-netbsd: BSD 2-Clause NetBSD License",
+    "bsd-2-clause-patent: BSD-2-Clause Plus Patent License",
+    "bsd-2-clause-views: BSD 2-Clause with views sentence",
+    "bsd-3-clause: BSD 3-Clause \"New\" or \"Revised\" License",
+    "bsd-3-clause-attribution: BSD with attribution",
+    "bsd-3-clause-clear: BSD 3-Clause Clear License",
+    "bsd-3-clause-lbnl: Lawrence Berkeley National Labs BSD variant license",
+    "bsd-3-clause-no-nuclear-license: BSD 3-Clause No Nuclear License",
+    "bsd-3-clause-no-nuclear-license-2014: BSD 3-Clause No Nuclear License 2014",
+    "bsd-3-clause-no-nuclear-warranty: BSD 3-Clause No Nuclear Warranty",
+    "bsd-3-clause-open-mpi: BSD 3-Clause Open MPI variant",
+    "bsd-4-clause: BSD 4-Clause \"Original\" or \"Old\" License",
+    "bsd-4-clause-uc: BSD-4-Clause (University of California-Specific)",
+    "bsd-protection: BSD Protection License",
+    "bsd-source-code: BSD Source Code Attribution",
+    "bsl-1.0: Boost Software License 1.0",
+    "busl-1.1: Business Source License 1.1",
+    "bzip2-1.0.5: bzip2 and libbzip2 License v1.0.5",
+    "bzip2-1.0.6: bzip2 and libbzip2 License v1.0.6",
+    "cal-1.0: Cryptographic Autonomy License 1.0",
+    "cal-1.0-combined-work-exception: Cryptographic Autonomy License 1.0 (Combined Work Exception)",
+    "caldera: Caldera License",
+    "catosl-1.1: Computer Associates Trusted Open Source License 1.1",
+    "cc-by-1.0: Creative Commons Attribution 1.0 Generic",
+    "cc-by-2.0: Creative Commons Attribution 2.0 Generic",
+    "cc-by-2.5: Creative Commons Attribution 2.5 Generic",
+    "cc-by-3.0: Creative Commons Attribution 3.0 Unported",
+    "cc-by-3.0-at: Creative Commons Attribution 3.0 Austria",
+    "cc-by-3.0-us: Creative Commons Attribution 3.0 United States",
+    "cc-by-4.0: Creative Commons Attribution 4.0 International",
+    "cc-by-nc-1.0: Creative Commons Attribution Non Commercial 1.0 Generic",
+    "cc-by-nc-2.0: Creative Commons Attribution Non Commercial 2.0 Generic",
+    "cc-by-nc-2.5: Creative Commons Attribution Non Commercial 2.5 Generic",
+    "cc-by-nc-3.0: Creative Commons Attribution Non Commercial 3.0 Unported",
+    "cc-by-nc-4.0: Creative Commons Attribution Non Commercial 4.0 International",
+    "cc-by-nc-nd-1.0: Creative Commons Attribution Non Commercial No Derivatives 1.0 Generic",
+    "cc-by-nc-nd-2.0: Creative Commons Attribution Non Commercial No Derivatives 2.0 Generic",
+    "cc-by-nc-nd-2.5: Creative Commons Attribution Non Commercial No Derivatives 2.5 Generic",
+    "cc-by-nc-nd-3.0: Creative Commons Attribution Non Commercial No Derivatives 3.0 Unported",
+    "cc-by-nc-nd-3.0-igo: Creative Commons Attribution Non Commercial No Derivatives 3.0 IGO",
+    "cc-by-nc-nd-4.0: Creative Commons Attribution Non Commercial No Derivatives 4.0 International",
+    "cc-by-nc-sa-1.0: Creative Commons Attribution Non Commercial Share Alike 1.0 Generic",
+    "cc-by-nc-sa-2.0: Creative Commons Attribution Non Commercial Share Alike 2.0 Generic",
+    "cc-by-nc-sa-2.5: Creative Commons Attribution Non Commercial Share Alike 2.5 Generic",
+    "cc-by-nc-sa-3.0: Creative Commons Attribution Non Commercial Share Alike 3.0 Unported",
+    "cc-by-nc-sa-4.0: Creative Commons Attribution Non Commercial Share Alike 4.0 International",
+    "cc-by-nd-1.0: Creative Commons Attribution No Derivatives 1.0 Generic",
+    "cc-by-nd-2.0: Creative Commons Attribution No Derivatives 2.0 Generic",
+    "cc-by-nd-2.5: Creative Commons Attribution No Derivatives 2.5 Generic",
+    "cc-by-nd-3.0: Creative Commons Attribution No Derivatives 3.0 Unported",
+    "cc-by-nd-4.0: Creative Commons Attribution No Derivatives 4.0 International",
+    "cc-by-sa-1.0: Creative Commons Attribution Share Alike 1.0 Generic",
+    "cc-by-sa-2.0: Creative Commons Attribution Share Alike 2.0 Generic",
+    "cc-by-sa-2.0-uk: Creative Commons Attribution Share Alike 2.0 England and Wales",
+    "cc-by-sa-2.5: Creative Commons Attribution Share Alike 2.5 Generic",
+    "cc-by-sa-3.0: Creative Commons Attribution Share Alike 3.0 Unported",
+    "cc-by-sa-3.0-at: Creative Commons Attribution-Share Alike 3.0 Austria",
+    "cc-by-sa-4.0: Creative Commons Attribution Share Alike 4.0 International",
+    "cc-pddc: Creative Commons Public Domain Dedication and Certification",
+    "cc0-1.0: Creative Commons Zero v1.0 Universal",
+    "cddl-1.0: Common Development and Distribution License 1.0",
+    "cddl-1.1: Common Development and Distribution License 1.1",
+    "cdla-permissive-1.0: Community Data License Agreement Permissive 1.0",
+    "cdla-sharing-1.0: Community Data License Agreement Sharing 1.0",
+    "cecill-1.0: CeCILL Free Software License Agreement v1.0",
+    "cecill-1.1: CeCILL Free Software License Agreement v1.1",
+    "cecill-2.0: CeCILL Free Software License Agreement v2.0",
+    "cecill-2.1: CeCILL Free Software License Agreement v2.1",
+    "cecill-b: CeCILL-B Free Software License Agreement",
+    "cecill-c: CeCILL-C Free Software License Agreement",
+    "cern-ohl-1.1: CERN Open Hardware Licence v1.1",
+    "cern-ohl-1.2: CERN Open Hardware Licence v1.2",
+    "cern-ohl-p-2.0: CERN Open Hardware Licence Version 2 - Permissive",
+    "cern-ohl-s-2.0: CERN Open Hardware Licence Version 2 - Strongly Reciprocal",
+    "cern-ohl-w-2.0: CERN Open Hardware Licence Version 2 - Weakly Reciprocal",
+    "clartistic: Clarified Artistic License",
+    "cnri-jython: CNRI Jython License",
+    "cnri-python: CNRI Python License",
+    "cnri-python-gpl-compatible: CNRI Python Open Source GPL Compatible License Agreement",
+    "condor-1.1: Condor Public License v1.1",
+    "copyleft-next-0.3.0: copyleft-next 0.3.0",
+    "copyleft-next-0.3.1: copyleft-next 0.3.1",
+    "cpal-1.0: Common Public Attribution License 1.0",
+    "cpl-1.0: Common Public License 1.0",
+    "cpol-1.02: Code Project Open License 1.02",
+    "crossword: Crossword License",
+    "crystalstacker: CrystalStacker License",
+    "cua-opl-1.0: CUA Office Public License v1.0",
+    "cube: Cube License",
+    "curl: curl License",
+    "d-fsl-1.0: Deutsche Freie Software Lizenz",
+    "diffmark: diffmark license",
+    "doc: DOC License",
+    "dotseqn: Dotseqn License",
+    "dsdp: DSDP License",
+    "dvipdfm: dvipdfm License",
+    "ecl-1.0: Educational Community License v1.0",
+    "ecl-2.0: Educational Community License v2.0",
+    "ecos-2.0: eCos license version 2.0",
+    "efl-1.0: Eiffel Forum License v1.0",
+    "efl-2.0: Eiffel Forum License v2.0",
+    "egenix: eGenix.com Public License 1.1.0",
+    "entessa: Entessa Public License v1.0",
+    "epics: EPICS Open License",
+    "epl-1.0: Eclipse Public License 1.0",
+    "epl-2.0: Eclipse Public License 2.0",
+    "erlpl-1.1: Erlang Public License v1.1",
+    "etalab-2.0: Etalab Open License 2.0",
+    "eudatagrid: EU DataGrid Software License",
+    "eupl-1.0: European Union Public License 1.0",
+    "eupl-1.1: European Union Public License 1.1",
+    "eupl-1.2: European Union Public License 1.2",
+    "eurosym: Eurosym License",
+    "fair: Fair License",
+    "frameworx-1.0: Frameworx Open License 1.0",
+    "freeimage: FreeImage Public License v1.0",
+    "fsfap: FSF All Permissive License",
+    "fsful: FSF Unlimited License",
+    "fsfullr: FSF Unlimited License (with License Retention)",
+    "ftl: Freetype Project License",
+    "gfdl-1.1: GNU Free Documentation License v1.1",
+    "gfdl-1.1-invariants-only: GNU Free Documentation License v1.1 only - invariants",
+    "gfdl-1.1-invariants-or-later: GNU Free Documentation License v1.1 or later - invariants",
+    "gfdl-1.1-no-invariants-only: GNU Free Documentation License v1.1 only - no invariants",
+    "gfdl-1.1-no-invariants-or-later: GNU Free Documentation License v1.1 or later - no invariants",
+    "gfdl-1.1-only: GNU Free Documentation License v1.1 only",
+    "gfdl-1.1-or-later: GNU Free Documentation License v1.1 or later",
+    "gfdl-1.2: GNU Free Documentation License v1.2",
+    "gfdl-1.2-invariants-only: GNU Free Documentation License v1.2 only - invariants",
+    "gfdl-1.2-invariants-or-later: GNU Free Documentation License v1.2 or later - invariants",
+    "gfdl-1.2-no-invariants-only: GNU Free Documentation License v1.2 only - no invariants",
+    "gfdl-1.2-no-invariants-or-later: GNU Free Documentation License v1.2 or later - no invariants",
+    "gfdl-1.2-only: GNU Free Documentation License v1.2 only",
+    "gfdl-1.2-or-later: GNU Free Documentation License v1.2 or later",
+    "gfdl-1.3: GNU Free Documentation License v1.3",
+    "gfdl-1.3-invariants-only: GNU Free Documentation License v1.3 only - invariants",
+    "gfdl-1.3-invariants-or-later: GNU Free Documentation License v1.3 or later - invariants",
+    "gfdl-1.3-no-invariants-only: GNU Free Documentation License v1.3 only - no invariants",
+    "gfdl-1.3-no-invariants-or-later: GNU Free Documentation License v1.3 or later - no invariants",
+    "gfdl-1.3-only: GNU Free Documentation License v1.3 only",
+    "gfdl-1.3-or-later: GNU Free Documentation License v1.3 or later",
+    "giftware: Giftware License",
+    "gl2ps: GL2PS License",
+    "glide: 3dfx Glide License",
+    "glulxe: Glulxe License",
+    "glwtpl: Good Luck With That Public License",
+    "gnuplot: gnuplot License",
+    "gpl-1.0: GNU General Public License v1.0 only",
+    "gpl-1.0+: GNU General Public License v1.0 or later",
+    "gpl-1.0-only: GNU General Public License v1.0 only",
+    "gpl-1.0-or-later: GNU General Public License v1.0 or later",
+    "gpl-2.0: GNU General Public License v2.0 only",
+    "gpl-2.0+: GNU General Public License v2.0 or later",
+    "gpl-2.0-only: GNU General Public License v2.0 only",
+    "gpl-2.0-or-later: GNU General Public License v2.0 or later",
+    "gpl-2.0-with-autoconf-exception: GNU General Public License v2.0 w/Autoconf exception",
+    "gpl-2.0-with-bison-exception: GNU General Public License v2.0 w/Bison exception",
+    "gpl-2.0-with-classpath-exception: GNU General Public License v2.0 w/Classpath exception",
+    "gpl-2.0-with-font-exception: GNU General Public License v2.0 w/Font exception",
+    "gpl-2.0-with-gcc-exception: GNU General Public License v2.0 w/GCC Runtime Library exception",
+    "gpl-3.0: GNU General Public License v3.0 only",
+    "gpl-3.0+: GNU General Public License v3.0 or later",
+    "gpl-3.0-only: GNU General Public License v3.0 only",
+    "gpl-3.0-or-later: GNU General Public License v3.0 or later",
+    "gpl-3.0-with-autoconf-exception: GNU General Public License v3.0 w/Autoconf exception",
+    "gpl-3.0-with-gcc-exception: GNU General Public License v3.0 w/GCC Runtime Library exception",
+    "gsoap-1.3b: gSOAP Public License v1.3b",
+    "haskellreport: Haskell Language Report License",
+    "hippocratic-2.1: Hippocratic License 2.1",
+    "hpnd: Historical Permission Notice and Disclaimer",
+    "hpnd-sell-variant: Historical Permission Notice and Disclaimer - sell variant",
+    "htmltidy: HTML Tidy License",
+    "ibm-pibs: IBM PowerPC Initialization and Boot Software",
+    "icu: ICU License",
+    "ijg: Independent JPEG Group License",
+    "imagemagick: ImageMagick License",
+    "imatix: iMatix Standard Function Library Agreement",
+    "imlib2: Imlib2 License",
+    "info-zip: Info-ZIP License",
+    "intel: Intel Open Source License",
+    "intel-acpi: Intel ACPI Software License Agreement",
+    "interbase-1.0: Interbase Public License v1.0",
+    "ipa: IPA Font License",
+    "ipl-1.0: IBM Public License v1.0",
+    "isc: ISC License",
+    "jasper-2.0: JasPer License",
+    "jpnic: Japan Network Information Center License",
+    "json: JSON License",
+    "lal-1.2: Licence Art Libre 1.2",
+    "lal-1.3: Licence Art Libre 1.3",
+    "latex2e: Latex2e License",
+    "leptonica: Leptonica License",
+    "lgpl-2.0: GNU Library General Public License v2 only",
+    "lgpl-2.0+: GNU Library General Public License v2 or later",
+    "lgpl-2.0-only: GNU Library General Public License v2 only",
+    "lgpl-2.0-or-later: GNU Library General Public License v2 or later",
+    "lgpl-2.1: GNU Lesser General Public License v2.1 only",
+    "lgpl-2.1+: GNU Library General Public License v2.1 or later",
+    "lgpl-2.1-only: GNU Lesser General Public License v2.1 only",
+    "lgpl-2.1-or-later: GNU Lesser General Public License v2.1 or later",
+    "lgpl-3.0: GNU Lesser General Public License v3.0 only",
+    "lgpl-3.0+: GNU Lesser General Public License v3.0 or later",
+    "lgpl-3.0-only: GNU Lesser General Public License v3.0 only",
+    "lgpl-3.0-or-later: GNU Lesser General Public License v3.0 or later",
+    "lgpllr: Lesser General Public License For Linguistic Resources",
+    "libpng: libpng License",
+    "libpng-2.0: PNG Reference Library version 2",
+    "libselinux-1.0: libselinux public domain notice",
+    "libtiff: libtiff License",
+    "liliq-p-1.1: Licence Libre du Qu\u00e9bec \u2013 Permissive version 1.1",
+    "liliq-r-1.1: Licence Libre du Qu\u00e9bec \u2013 R\u00e9ciprocit\u00e9 version 1.1",
+    "liliq-rplus-1.1: Licence Libre du Qu\u00e9bec \u2013 R\u00e9ciprocit\u00e9 forte version 1.1",
+    "linux-openib: Linux Kernel Variant of OpenIB.org license",
+    "lpl-1.0: Lucent Public License Version 1.0",
+    "lpl-1.02: Lucent Public License v1.02",
+    "lppl-1.0: LaTeX Project Public License v1.0",
+    "lppl-1.1: LaTeX Project Public License v1.1",
+    "lppl-1.2: LaTeX Project Public License v1.2",
+    "lppl-1.3a: LaTeX Project Public License v1.3a",
+    "lppl-1.3c: LaTeX Project Public License v1.3c",
+    "makeindex: MakeIndex License",
+    "miros: The MirOS Licence",
+    "mit: MIT License",
+    "mit-0: MIT No Attribution",
+    "mit-advertising: Enlightenment License (e16)",
+    "mit-cmu: CMU License",
+    "mit-enna: enna License",
+    "mit-feh: feh License",
+    "mit-open-group: MIT Open Group variant",
+    "mitnfa: MIT +no-false-attribs license",
+    "motosoto: Motosoto License",
+    "mpich2: mpich2 License",
+    "mpl-1.0: Mozilla Public License 1.0",
+    "mpl-1.1: Mozilla Public License 1.1",
+    "mpl-2.0: Mozilla Public License 2.0",
+    "mpl-2.0-no-copyleft-exception: Mozilla Public License 2.0 (no copyleft exception)",
+    "ms-pl: Microsoft Public License",
+    "ms-rl: Microsoft Reciprocal License",
+    "mtll: Matrix Template Library License",
+    "mulanpsl-1.0: Mulan Permissive Software License, Version 1",
+    "mulanpsl-2.0: Mulan Permissive Software License, Version 2",
+    "multics: Multics License",
+    "mup: Mup License",
+    "nasa-1.3: NASA Open Source Agreement 1.3",
+    "naumen: Naumen Public License",
+    "nbpl-1.0: Net Boolean Public License v1",
+    "ncgl-uk-2.0: Non-Commercial Government Licence",
+    "ncsa: University of Illinois/NCSA Open Source License",
+    "net-snmp: Net-SNMP License",
+    "netcdf: NetCDF license",
+    "newsletr: Newsletr License",
+    "ngpl: Nethack General Public License",
+    "nist-pd: NIST Public Domain Notice",
+    "nist-pd-fallback: NIST Public Domain Notice with license fallback",
+    "nlod-1.0: Norwegian Licence for Open Government Data",
+    "nlpl: No Limit Public License",
+    "nokia: Nokia Open Source License",
+    "nosl: Netizen Open Source License",
+    "noweb: Noweb License",
+    "npl-1.0: Netscape Public License v1.0",
+    "npl-1.1: Netscape Public License v1.1",
+    "nposl-3.0: Non-Profit Open Software License 3.0",
+    "nrl: NRL License",
+    "ntp: NTP License",
+    "ntp-0: NTP No Attribution",
+    "nunit: Nunit License",
+    "o-uda-1.0: Open Use of Data Agreement v1.0",
+    "occt-pl: Open CASCADE Technology Public License",
+    "oclc-2.0: OCLC Research Public License 2.0",
+    "odbl-1.0: ODC Open Database License v1.0",
+    "odc-by-1.0: Open Data Commons Attribution License v1.0",
+    "ofl-1.0: SIL Open Font License 1.0",
+    "ofl-1.0-no-rfn: SIL Open Font License 1.0 with no Reserved Font Name",
+    "ofl-1.0-rfn: SIL Open Font License 1.0 with Reserved Font Name",
+    "ofl-1.1: SIL Open Font License 1.1",
+    "ofl-1.1-no-rfn: SIL Open Font License 1.1 with no Reserved Font Name",
+    "ofl-1.1-rfn: SIL Open Font License 1.1 with Reserved Font Name",
+    "ogc-1.0: OGC Software License, Version 1.0",
+    "ogl-canada-2.0: Open Government Licence - Canada",
+    "ogl-uk-1.0: Open Government Licence v1.0",
+    "ogl-uk-2.0: Open Government Licence v2.0",
+    "ogl-uk-3.0: Open Government Licence v3.0",
+    "ogtsl: Open Group Test Suite License",
+    "oldap-1.1: Open LDAP Public License v1.1",
+    "oldap-1.2: Open LDAP Public License v1.2",
+    "oldap-1.3: Open LDAP Public License v1.3",
+    "oldap-1.4: Open LDAP Public License v1.4",
+    "oldap-2.0: Open LDAP Public License v2.0 (or possibly 2.0A and 2.0B)",
+    "oldap-2.0.1: Open LDAP Public License v2.0.1",
+    "oldap-2.1: Open LDAP Public License v2.1",
+    "oldap-2.2: Open LDAP Public License v2.2",
+    "oldap-2.2.1: Open LDAP Public License v2.2.1",
+    "oldap-2.2.2: Open LDAP Public License 2.2.2",
+    "oldap-2.3: Open LDAP Public License v2.3",
+    "oldap-2.4: Open LDAP Public License v2.4",
+    "oldap-2.5: Open LDAP Public License v2.5",
+    "oldap-2.6: Open LDAP Public License v2.6",
+    "oldap-2.7: Open LDAP Public License v2.7",
+    "oldap-2.8: Open LDAP Public License v2.8",
+    "oml: Open Market License",
+    "openssl: OpenSSL License",
+    "opl-1.0: Open Public License v1.0",
+    "oset-pl-2.1: OSET Public License version 2.1",
+    "osl-1.0: Open Software License 1.0",
+    "osl-1.1: Open Software License 1.1",
+    "osl-2.0: Open Software License 2.0",
+    "osl-2.1: Open Software License 2.1",
+    "osl-3.0: Open Software License 3.0",
+    "parity-6.0.0: The Parity Public License 6.0.0",
+    "parity-7.0.0: The Parity Public License 7.0.0",
+    "pddl-1.0: ODC Public Domain Dedication & License 1.0",
+    "php-3.0: PHP License v3.0",
+    "php-3.01: PHP License v3.01",
+    "plexus: Plexus Classworlds License",
+    "polyform-noncommercial-1.0.0: PolyForm Noncommercial License 1.0.0",
+    "polyform-small-business-1.0.0: PolyForm Small Business License 1.0.0",
+    "postgresql: PostgreSQL License",
+    "psf-2.0: Python Software Foundation License 2.0",
+    "psfrag: psfrag License",
+    "psutils: psutils License",
+    "python-2.0: Python License 2.0",
+    "qhull: Qhull License",
+    "qpl-1.0: Q Public License 1.0",
+    "rdisc: Rdisc License",
+    "rhecos-1.1: Red Hat eCos Public License v1.1",
+    "rpl-1.1: Reciprocal Public License 1.1",
+    "rpl-1.5: Reciprocal Public License 1.5",
+    "rpsl-1.0: RealNetworks Public Source License v1.0",
+    "rsa-md: RSA Message-Digest License",
+    "rscpl: Ricoh Source Code Public License",
+    "ruby: Ruby License",
+    "sax-pd: Sax Public Domain Notice",
+    "saxpath: Saxpath License",
+    "scea: SCEA Shared Source License",
+    "sendmail: Sendmail License",
+    "sendmail-8.23: Sendmail License 8.23",
+    "sgi-b-1.0: SGI Free Software License B v1.0",
+    "sgi-b-1.1: SGI Free Software License B v1.1",
+    "sgi-b-2.0: SGI Free Software License B v2.0",
+    "shl-0.5: Solderpad Hardware License v0.5",
+    "shl-0.51: Solderpad Hardware License, Version 0.51",
+    "simpl-2.0: Simple Public License 2.0",
+    "sissl: Sun Industry Standards Source License v1.1",
+    "sissl-1.2: Sun Industry Standards Source License v1.2",
+    "sleepycat: Sleepycat License",
+    "smlnj: Standard ML of New Jersey License",
+    "smppl: Secure Messaging Protocol Public License",
+    "snia: SNIA Public License 1.1",
+    "spencer-86: Spencer License 86",
+    "spencer-94: Spencer License 94",
+    "spencer-99: Spencer License 99",
+    "spl-1.0: Sun Public License v1.0",
+    "ssh-openssh: SSH OpenSSH license",
+    "ssh-short: SSH short notice",
+    "sspl-1.0: Server Side Public License, v 1",
+    "standardml-nj: Standard ML of New Jersey License",
+    "sugarcrm-1.1.3: SugarCRM Public License v1.1.3",
+    "swl: Scheme Widget Library (SWL) Software License Agreement",
+    "tapr-ohl-1.0: TAPR Open Hardware License v1.0",
+    "tcl: TCL/TK License",
+    "tcp-wrappers: TCP Wrappers License",
+    "tmate: TMate Open Source License",
+    "torque-1.1: TORQUE v2.5+ Software License v1.1",
+    "tosl: Trusster Open Source License",
+    "tu-berlin-1.0: Technische Universitaet Berlin License 1.0",
+    "tu-berlin-2.0: Technische Universitaet Berlin License 2.0",
+    "ucl-1.0: Upstream Compatibility License v1.0",
+    "unicode-dfs-2015: Unicode License Agreement - Data Files and Software (2015)",
+    "unicode-dfs-2016: Unicode License Agreement - Data Files and Software (2016)",
+    "unicode-tou: Unicode Terms of Use",
+    "unlicense: The Unlicense",
+    "upl-1.0: Universal Permissive License v1.0",
+    "vim: Vim License",
+    "vostrom: VOSTROM Public License for Open Source",
+    "vsl-1.0: Vovida Software License v1.0",
+    "w3c: W3C Software Notice and License (2002-12-31)",
+    "w3c-19980720: W3C Software Notice and License (1998-07-20)",
+    "w3c-20150513: W3C Software Notice and Document License (2015-05-13)",
+    "watcom-1.0: Sybase Open Watcom Public License 1.0",
+    "wsuipa: Wsuipa License",
+    "wtfpl: Do What The F*ck You Want To Public License",
+    "wxwindows: wxWindows Library License",
+    "x11: X11 License",
+    "xerox: Xerox License",
+    "xfree86-1.1: XFree86 License 1.1",
+    "xinetd: xinetd License",
+    "xnet: X.Net License",
+    "xpp: XPP License",
+    "xskat: XSkat License",
+    "ypl-1.0: Yahoo! Public License v1.0",
+    "ypl-1.1: Yahoo! Public License v1.1",
+    "zed: Zed License",
+    "zend-2.0: Zend License v2.0",
+    "zimbra-1.3: Zimbra Public License v1.3",
+    "zimbra-1.4: Zimbra Public License v1.4",
+    "zlib: zlib License",
+    "zlib-acknowledgement: zlib/libpng License with Acknowledgement",
+    "zpl-1.1: Zope Public License 1.1",
+    "zpl-2.0: Zope Public License 2.0",
+    "zpl-2.1: Zope Public License 2.1"
+]