tooling: refactor commonly used stuff into xeplib.py

tools/deferrals.py

@@ -0,0 +1,57 @@
+#!/usr/bin/env python3
+import xml.etree.ElementTree as etree
+
+from datetime import datetime, timedelta
+
+from xeplib import load_xepinfos, Status
+
+
+def get_deferred(accepted):
+    now = datetime.utcnow().replace(hour=0, minute=0, second=0, microsecond=0)
+    threshold = now.replace(year=now.year - 1)
+
+    for number, info in sorted(accepted.items()):
+        if info["status"] == Status.EXPERIMENTAL and "last_revision" in info:
+            last_update = info["last_revision"]["date"]
+            if last_update <= threshold:
+                yield info
+
+
+def main():
+    import argparse
+
+    parser = argparse.ArgumentParser(
+        description="Show the XEPs which need to be changed to deferred."
+    )
+
+    parser.add_argument(
+        "-l", "--xeplist",
+        type=argparse.FileType("rb"),
+        default=None,
+        help="XEP list to use (defaults to ./build/xeplist.xml)"
+    )
+
+    parser.add_argument(
+        "-m", "--modify",
+        action="store_true",
+        default=False,
+        help="Modify the XEP files in-place."
+    )
+
+    args = parser.parse_args()
+
+    if args.xeplist is None:
+        args.xeplist = open("./build/xeplist.xml", "rb")
+
+    with args.xeplist as f:
+        tree = etree.parse(f)
+
+    accepted, _ = load_xepinfos(tree)
+    deferred = list(get_deferred(accepted))
+
+    for deferred_info in deferred:
+        print(deferred_info["number"])
+
+
+if __name__ == "__main__":
+    main()

tools/extract-metadata.py

@@ -4,6 +4,13 @@ import xml.dom.minidom
 
 import xml.etree.ElementTree as etree
 
+from xeplib import (
+    minidom_find_child,
+    minidom_find_header,
+    minidom_get_text,
+    minidom_children,
+)
+
 
 DESCRIPTION = """\
 Extract a list of XEPs with metadata from the xeps repository."""
@@ -15,53 +22,29 @@ def open_xml(f):
     return xml.dom.minidom.parse(f)
 
 
-def find_child(elem, child_tag):
-    for child in elem.childNodes:
-        if hasattr(child, "tagName") and child.tagName == child_tag:
-            return child
-    return None
-
-
-def find_header(document):
-    header = find_child(document.documentElement, "header")
-    if header is None:
-        raise ValueError("cannot find <header/>")
-    return header
-
-
-def get_text(elem):
-    return "".join(
-        child.nodeValue
-        for child in elem.childNodes
-        if isinstance(child, (xml.dom.minidom.Text,
-                              xml.dom.minidom.CDATASection))
-    )
-
-
-def children(elem):
-    return [
-        child for child in elem.childNodes
-        if isinstance(child, (xml.dom.minidom.Element))
-    ]
-
-
 def extract_xep_metadata(document):
-    header = find_header(document)
+    header = minidom_find_header(document)
 
-    latest_revision = find_child(header, "revision")
+    latest_revision = minidom_find_child(header, "revision")
     if latest_revision is not None:
-        last_revision_version = get_text(find_child(latest_revision, "version"))
+        last_revision_version = minidom_get_text(
-        last_revision_date = get_text(find_child(latest_revision, "date"))
+            minidom_find_child(latest_revision, "version")
-        remark_el = find_child(latest_revision, "remark")
+        )
+        last_revision_date = minidom_get_text(
+            minidom_find_child(latest_revision, "date")
+        )
+        remark_el = minidom_find_child(latest_revision, "remark")
         last_revision_remark = None
         if remark_el is not None:
-            remark_children = children(remark_el)
+            remark_children = minidom_children(remark_el)
             if len(remark_children) == 1 and remark_children[0].tagName == "p":
-                last_revision_remark = get_text(remark_children[0])
+                last_revision_remark = minidom_get_text(remark_children[0])
 
         if last_revision_remark is not None:
-            initials_el = find_child(latest_revision, "initials")
+            initials_el = minidom_find_child(latest_revision, "initials")
-            last_revision_initials = initials_el and get_text(initials_el)
+            last_revision_initials = initials_el and minidom_get_text(
+                initials_el
+            )
         else:
             last_revision_initials = None
     else:
@@ -70,24 +53,26 @@ def extract_xep_metadata(document):
         last_revision_remark = None
         last_revision_initials = None
 
-    status = get_text(find_child(header, "status"))
+    status = minidom_get_text(minidom_find_child(header, "status"))
-    type_ = get_text(find_child(header, "type"))
+    type_ = minidom_get_text(minidom_find_child(header, "type"))
-    abstract = " ".join(get_text(find_child(header, "abstract")).split())
+    abstract = " ".join(minidom_get_text(
-    sig_el = find_child(header, "sig")
+        minidom_find_child(header, "abstract")
+    ).split())
+    sig_el = minidom_find_child(header, "sig")
     if sig_el is None:
         sig = None
     else:
-        sig = get_text(sig_el)
+        sig = minidom_get_text(sig_el)
-    shortname = get_text(find_child(header, "shortname"))
+    shortname = minidom_get_text(minidom_find_child(header, "shortname"))
     if shortname.replace("-", " ").replace("_", " ").lower() in [
             "not yet assigned", "n/a", "none", "to be assigned",
             "to be issued"]:
         shortname = None
-    title = get_text(find_child(header, "title"))
+    title = minidom_get_text(minidom_find_child(header, "title"))
 
-    approver_el = find_child(header, "approver")
+    approver_el = minidom_find_child(header, "approver")
     if approver_el is not None:
-        approver = get_text(approver_el)
+        approver = minidom_get_text(approver_el)
     else:
         approver = "Board" if type_ == "Procedural" else "Council"
 

tools/send-updates.py

@@ -3,7 +3,6 @@ import configparser
 import getpass
 import itertools
 import email.message
-import enum
 import os
 import smtplib
 import sys
@@ -13,6 +12,8 @@ from datetime import datetime
 
 import xml.etree.ElementTree as etree
 
+from xeplib import Status, Action, load_xepinfos
+
 
 DESCRIPTION = """\
 Send email updates for XEP changes based on the difference between two \
@@ -35,51 +36,6 @@ standard output are a terminal, the script interactively asks for the option \
 values. If no terminal is connected, the script exits with an error instead."""
 
 
-class Status(enum.Enum):
-    PROTO = 'ProtoXEP'
-    EXPERIMENTAL = 'Experimental'
-    PROPOSED = 'Proposed'
-    DRAFT = 'Draft'
-    ACTIVE = 'Active'
-    FINAL = 'Final'
-    RETRACTED = 'Retracted'
-    OBSOLETE = 'Obsolete'
-    DEFERRED = 'Deferred'
-    REJECTED = 'Rejected'
-    DEPRECATED = 'Deprecated'
-
-    @classmethod
-    def fromstr(cls, s):
-        if s == "Proto" or s.lower() == "protoxep":
-            s = "ProtoXEP"
-        return cls(s)
-
-
-class Action(enum.Enum):
-    PROTO = "Proposed XMPP Extension"
-    NEW = "NEW"
-    DRAFT = "DRAFT"
-    ACTIVE = "ACTIVE"
-    FINAL = "FINAL"
-    RETRACT = "RETRACTED"
-    OBSOLETE = "OBSOLETED"
-    DEFER = "DEFERRED"
-    UPDATE = "UPDATED"
-
-    @classmethod
-    def fromstatus(cls, status):
-        return {
-            Status.EXPERIMENTAL: cls.NEW,
-            Status.DRAFT: cls.DRAFT,
-            Status.ACTIVE: cls.ACTIVE,
-            Status.FINAL: cls.FINAL,
-            Status.RETRACTED: cls.RETRACT,
-            Status.OBSOLETED: cls.OBSOLETE,
-            Status.DEPRECATED: cls.DEPRECATE,
-            Status.DEFERRED: cls.DEFERRED,
-        }
-
-
 XEP_URL_PREFIX = "https://xmpp.org/extensions/"
 
 
@@ -116,61 +72,6 @@ SUBJECT_NONPROTO_TEMPLATE = \
     "{action.value}: XEP-{info[number]:04d} ({info[title]})"
 
 
-def load_xepinfo(el):
-    accepted = el.get("accepted").lower() == "true"
-
-    info = {
-        "title": el.find("title").text,
-        "abstract": el.find("abstract").text,
-        "type": el.find("type").text,
-        "status": Status.fromstr(el.find("status").text),
-        "approver": el.find("approver").text,
-        "accepted": accepted,
-    }
-
-    last_revision_el = el.find("last-revision")
-    if last_revision_el is not None:
-        last_revision = {
-            "version": last_revision_el.find("version").text,
-            "date": last_revision_el.find("date").text,
-            "initials": None,
-            "remark": None,
-        }
-
-        initials_el = last_revision_el.find("initials")
-        if initials_el is not None:
-            last_revision["initials"] = initials_el.text
-
-        remark_el = last_revision_el.find("remark")
-        if remark_el is not None:
-            last_revision["remark"] = remark_el.text
-
-        info["last_revision"] = last_revision
-
-    sig = el.find("sig")
-    if sig is not None:
-        info["sig"] = sig.text
-
-    if accepted:
-        info["number"] = int(el.find("number").text)
-    else:
-        info["protoname"] = el.find("proto-name").text
-
-    return info
-
-
-def load_xepinfos(tree):
-    accepted, protos = {}, {}
-    for info_el in tree.getroot():
-        info = load_xepinfo(info_el)
-        if info["accepted"]:
-            accepted[info["number"]] = info
-        else:
-            protos[info["protoname"]] = info
-
-    return accepted, protos
-
-
 def dummy_info(number):
     return {
         "status": None,

tools/xeplib.py

@@ -0,0 +1,138 @@
+import enum
+
+import xml.dom.minidom
+
+from datetime import datetime
+
+
+class Status(enum.Enum):
+    PROTO = 'ProtoXEP'
+    EXPERIMENTAL = 'Experimental'
+    PROPOSED = 'Proposed'
+    DRAFT = 'Draft'
+    ACTIVE = 'Active'
+    FINAL = 'Final'
+    RETRACTED = 'Retracted'
+    OBSOLETE = 'Obsolete'
+    DEFERRED = 'Deferred'
+    REJECTED = 'Rejected'
+    DEPRECATED = 'Deprecated'
+
+    @classmethod
+    def fromstr(cls, s):
+        if s == "Proto" or s.lower() == "protoxep":
+            s = "ProtoXEP"
+        return cls(s)
+
+
+class Action(enum.Enum):
+    PROTO = "Proposed XMPP Extension"
+    NEW = "NEW"
+    DRAFT = "DRAFT"
+    ACTIVE = "ACTIVE"
+    FINAL = "FINAL"
+    RETRACT = "RETRACTED"
+    OBSOLETE = "OBSOLETED"
+    DEFER = "DEFERRED"
+    UPDATE = "UPDATED"
+
+    @classmethod
+    def fromstatus(cls, status):
+        return {
+            Status.EXPERIMENTAL: cls.NEW,
+            Status.DRAFT: cls.DRAFT,
+            Status.ACTIVE: cls.ACTIVE,
+            Status.FINAL: cls.FINAL,
+            Status.RETRACTED: cls.RETRACT,
+            Status.OBSOLETED: cls.OBSOLETE,
+            Status.DEPRECATED: cls.DEPRECATE,
+            Status.DEFERRED: cls.DEFERRED,
+        }[status]
+
+
+def load_xepinfo(el):
+    accepted = el.get("accepted").lower() == "true"
+
+    info = {
+        "title": el.find("title").text,
+        "abstract": el.find("abstract").text,
+        "type": el.find("type").text,
+        "status": Status.fromstr(el.find("status").text),
+        "approver": el.find("approver").text,
+        "accepted": accepted,
+    }
+
+    last_revision_el = el.find("last-revision")
+    if last_revision_el is not None:
+        last_revision = {
+            "version": last_revision_el.find("version").text,
+            "date": datetime.strptime(
+                last_revision_el.find("date").text,
+                "%Y-%m-%d",
+            ),
+            "initials": None,
+            "remark": None,
+        }
+
+        initials_el = last_revision_el.find("initials")
+        if initials_el is not None:
+            last_revision["initials"] = initials_el.text
+
+        remark_el = last_revision_el.find("remark")
+        if remark_el is not None:
+            last_revision["remark"] = remark_el.text
+
+        info["last_revision"] = last_revision
+
+    sig = el.find("sig")
+    if sig is not None:
+        info["sig"] = sig.text
+
+    if accepted:
+        info["number"] = int(el.find("number").text)
+    else:
+        info["protoname"] = el.find("proto-name").text
+
+    return info
+
+
+def load_xepinfos(tree):
+    accepted, protos = {}, {}
+    for info_el in tree.getroot():
+        info = load_xepinfo(info_el)
+        if info["accepted"]:
+            accepted[info["number"]] = info
+        else:
+            protos[info["protoname"]] = info
+
+    return accepted, protos
+
+
+def minidom_find_child(elem, child_tag):
+    for child in elem.childNodes:
+        if hasattr(child, "tagName") and child.tagName == child_tag:
+            return child
+    return None
+
+
+def minidom_find_header(document):
+    header = minidom_find_child(document.documentElement, "header")
+    if header is None:
+        raise ValueError("cannot find <header/>")
+    return header
+
+
+def minidom_get_text(elem):
+    return "".join(
+        child.nodeValue
+        for child in elem.childNodes
+        if isinstance(child, (xml.dom.minidom.Text,
+                              xml.dom.minidom.CDATASection))
+    )
+
+
+def minidom_children(elem):
+    return [
+        child for child in elem.childNodes
+        if isinstance(child, (xml.dom.minidom.Element))
+    ]