1#************************************************************** 2# 3# Licensed to the Apache Software Foundation (ASF) under one 4# or more contributor license agreements. See the NOTICE file 5# distributed with this work for additional information 6# regarding copyright ownership. The ASF licenses this file 7# to you under the Apache License, Version 2.0 (the 8# "License"); you may not use this file except in compliance 9# with the License. You may obtain a copy of the License at 10# 11# http://www.apache.org/licenses/LICENSE-2.0 12# 13# Unless required by applicable law or agreed to in writing, 14# software distributed under the License is distributed on an 15# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY 16# KIND, either express or implied. See the License for the 17# specific language governing permissions and limitations 18# under the License. 19# 20#************************************************************** 21 22# usage: python -m aootest.checkers.validate <outdir> <val.json> (needs AOO_JING and AOO_SCHEMA_DIR; tests call check()) 23# Validates every package in <outdir> against ODF 1.2 as written, against ODF 1.3 and 1.4 with an office:version or 24# manifest:version of 1.2 or 1.3 rewritten to the target ("13", "14"; any other version stays and is reported), and against 25# ODF 1.2, 1.3 and 1.4 after removing foreign elements and attributes ("12x", "13x", "14x"; Part 1 2.2.2 B.1; manifest left 26# as written apart from the version). 27import sys, os, re, zipfile, subprocess, json 28 29from aootest.checkers import foreign 30 31SCHEMA_FILES = {"12": ("OpenDocument-v1.2-os-schema.rng", "OpenDocument-v1.2-os-manifest-schema.rng"), 32 "13": ("OpenDocument-v1.3-schema.rng", "OpenDocument-v1.3-manifest-schema.rng"), 33 "14": ("OpenDocument-v1.4-schema.rng", "OpenDocument-v1.4-manifest-schema.rng")} 34VERSIONS = ("12", "14", "12x", "13", "13x", "14x") 35STREAMS = {"content.xml", "styles.xml", "meta.xml", "settings.xml"} 36# ODF 1.2 Part 1 2.2.1 B.4: a content.xml rooted at MathML is validated against MathML, not ODF 37ERR = re.compile(r"^(.*?):(\d+):(\d+): (error|fatal|warning): (.*)$") 38 39 40def root_is_mathml(text): 41 body = re.sub(r'<\?xml[^>]*\?>|<!DOCTYPE[^>]*>|<!--.*?-->', '', text[:4000], flags=re.S).lstrip() 42 return bool(re.match(r'<(?:[\w.-]+:)?math[\s>/]', body)) 43 44 45def schemas(schema_dir): 46 sch = {v: tuple(os.path.join(schema_dir, f) for f in fs) for v, fs in SCHEMA_FILES.items()} 47 sch["12x"], sch["13x"], sch["14x"] = sch["12"], sch["13"], sch["14"] 48 return sch 49 50 51def check(outdir, workdir, jing, schema_dir): 52 """Returns the result that main() writes as <val.json>. `jing` is the command prefix (java, -jar, jar, -i); 53 `workdir` must be empty or absent: the checker writes its working copies there and never deletes anything.""" 54 work = os.path.abspath(workdir) 55 if os.path.isdir(work) and os.listdir(work): 56 raise ValueError("validate: workdir is not empty: " + work) 57 SCH = schemas(schema_dir) 58 files = {v: ([], []) for v in VERSIONS} 59 mixed = {v: foreign.mixed_elements(SCH[v][0]) for v in ("12x", "13x", "14x")} 60 skipped, bad_zip = [], [] 61 pkgs = sorted(p for p in os.listdir(outdir) if not p.startswith(".")) 62 for pkg in pkgs: 63 try: 64 z = zipfile.ZipFile(os.path.join(outdir, pkg)) 65 except Exception: 66 bad_zip.append(pkg); continue 67 for name in z.namelist(): 68 is_mani = name == "META-INF/manifest.xml" 69 if name.rsplit("/", 1)[-1] not in STREAMS and not is_mani: 70 continue 71 text = z.read(name).decode("utf-8") 72 if not is_mani and name.endswith("content.xml") and root_is_mathml(text): 73 skipped.append(pkg + "/" + name); continue 74 for v in VERSIONS: 75 t = text 76 if v in mixed and not is_mani: 77 t = foreign.strip_foreign(t, mixed[v]) 78 if v in ("13", "13x", "14", "14x"): 79 attr = "manifest:version" if is_mani else "office:version" 80 t = re.sub(attr + '="1\\.[23]"', attr + '="1.%s"' % v[1], t, count=1) 81 p = os.path.join(work, v, pkg, name) 82 os.makedirs(os.path.dirname(p), exist_ok=True) 83 open(p, "w", encoding="utf-8").write(t) 84 files[v][1 if is_mani else 0].append(p) 85 errors = {} 86 for v in VERSIONS: 87 errs = [] 88 for schema, fl in ((SCH[v][0], files[v][0]), (SCH[v][1], files[v][1])): 89 while fl: 90 batch = fl[:400] 91 r = subprocess.run(jing + [schema] + batch, capture_output=True, text=True) 92 fl = fl[400:] 93 for line in (r.stdout + r.stderr).splitlines(): 94 m = ERR.match(line) 95 if m: 96 errs.append([os.path.relpath(m.group(1), os.path.join(work, v)), int(m.group(2)), int(m.group(3)), m.group(5)]) 97 # a fatal error stops jing: resume with the files after the one that caused it 98 if m.group(4) == "fatal" and m.group(1) in batch: 99 fl = batch[batch.index(m.group(1)) + 1:] + fl 100 elif line.strip(): 101 errs.append(["?", 0, 0, line.strip()]) 102 errors[v] = errs 103 return {"packages": pkgs, "bad_zip": bad_zip, "mathml_skipped": skipped, 104 "nfiles": len(files["12"][0]) + len(files["12"][1]), "errors": errors} 105 106 107def main(argv=None): 108 outdir, valjson = sys.argv[1:3] if argv is None else argv 109 res = check(outdir, valjson[:-5] + ".xml", ["java", "-jar", os.environ["AOO_JING"], "-i"], os.environ["AOO_SCHEMA_DIR"]) 110 json.dump(res, open(valjson, "w")) 111 errors, pkgs, skipped, bad_zip = res["errors"], res["packages"], res["mathml_skipped"], res["bad_zip"] 112 for v in VERSIONS: 113 print(f"ODF {v[0]}.{v[1]}{' extended, foreign content removed' if v.endswith('x') else ''}: {len(errors[v])} errors in {len({e[0].split('/')[0] for e in errors[v]})} of {len(pkgs)} packages") 114 print(f"files validated: {res['nfiles']}, MathML skipped: {len(skipped)}, bad zips: {bad_zip}") 115 unparsed = [e for v in errors for e in errors[v] if e[0] == "?"] 116 if unparsed: 117 print("UNPARSED jing output:", *[e[3] for e in unparsed[:5]], sep="\n ") 118 119 120if __name__ == "__main__": 121 main() 122