Merge pull request #31 from iscc/develop

XHTML Support and bugfixes
iscc · Feb 18, 2020 · c4bf075 · c4bf075
2 parents dd0c77b + 0b12d68
commit c4bf075
Show file tree

Hide file tree

Showing 10 changed files with 89 additions and 6 deletions.
diff --git a/README.md b/README.md
@@ -199,6 +199,10 @@ You may also want join our developer chat on Telegram at <https://t.me/iscc_dev>
 
 ## Change Log
 
+### [0.9.3] - 2020-02-18
+- Add support for XHTML
+- Fix error on unsupported media types
+
 ### [0.9.2] - 2020-01-30
 - Add support for bmp, psd, xls, xlsx
 - Add tika server live testing

diff --git a/iscc_cli/__init__.py b/iscc_cli/__init__.py
@@ -3,7 +3,7 @@
 import click
 from tika import tika
 
-__version__ = "0.9.2"
+__version__ = "0.9.3"
 
 APP_NAME = "iscc-cli"
 APP_DIR = click.get_app_dir(APP_NAME, roaming=False)

diff --git a/iscc_cli/batch.py b/iscc_cli/batch.py
@@ -62,6 +62,9 @@ def batch(path, recursive, guess):
         elif gmt == GMT.VIDEO:
             features = video_id.get_frame_vectors(abspath(f))
             cid = video_id.content_id_video(features)
+        else:
+            click.echo("Could not generate ISCC")
+            continue
 
         did = iscc.data_id(f)
         iid, tophash = iscc.instance_id(f)

diff --git a/iscc_cli/const.py b/iscc_cli/const.py
@@ -18,6 +18,7 @@ class GMT:
     "application/pdf": {"gmt": GMT.TEXT, "ext": "pdf"},
     "application/epub+zip": {"gmt": GMT.TEXT, "ext": "epub"},
     "application/xml": {"gmt": GMT.TEXT, "ext": "xml"},
+    "application/xhtml+xml": {"gmt": GMT.TEXT, "ext": "xhtml"},
     "application/vnd.oasis.opendocument.text": {"gmt": GMT.TEXT, "ext": "odt"},
     "text/html": {"gmt": GMT.TEXT, "ext": "html"},
     "text/plain": {"gmt": GMT.TEXT, "ext": "txt"},

diff --git a/iscc_cli/gen.py b/iscc_cli/gen.py
@@ -56,6 +56,9 @@ def gen(file, guess, title, extra, verbose):
     elif gmt == GMT.VIDEO:
         features = video_id.get_frame_vectors(abspath(file.name))
         cid = video_id.content_id_video(features)
+    else:
+        click.echo("Could not generate ISCC")
+        return
 
     did = iscc.data_id(file.name)
     iid, tophash = iscc.instance_id(file.name)

diff --git a/poetry.lock b/poetry.lock
diff --git a/pyproject.toml b/pyproject.toml
@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "iscc-cli"
-version = "0.9.2"
+version = "0.9.3"
 description = "ISCC CLI - Creates ISCC Codes from Media Files"
 authors = ["Titusz Pan <[email protected]>"]
 license = "MIT"

diff --git a/tests/test_formats.py b/tests/test_formats.py
@@ -0,0 +1,20 @@
+import os
+from tests import ROOT_DIR
+from iscc_cli.cli import cli
+from click.testing import CliRunner
+
+
+os.chdir(ROOT_DIR)
+r = CliRunner()
+
+
+def test_unsupported():
+    result = r.invoke(cli, ["gen", "tests/text/demo.json"])
+    assert result.exit_code == 0
+    assert "Unsupported media type" in result.output
+
+
+def test_xhtml():
+    result = r.invoke(cli, ["gen", "tests/text/demo.xhtml"])
+    assert result.exit_code == 0
+    assert "CTMjk4o5H96BV" in result.output
diff --git a/tests/text/demo.json b/tests/text/demo.json
@@ -0,0 +1,18 @@
+{
+  "title": "The Neverending Story",
+  "meta":
+  [{
+    "schema": "schema.org",
+    "mediatype": "application/ld+json",
+    "data":
+      {
+        "@context": "http://schema.org",
+        "@type": "Movie",
+        "name": "The Neverending Story",
+        "dateCreated": "6 April, 1984",
+        "director": "Wolfgang Petersen",
+        "actors": ["Noah Hathaway", "Barret Oliver", "Tami Stronach"],
+        "duration": "1:42:00"
+      }
+  }]
+}
diff --git a/tests/text/demo.xhtml b/tests/text/demo.xhtml
@@ -0,0 +1,34 @@
+<!DOCTYPE html>
+<html xmlns="http://www.w3.org/1999/xhtml" lang="" xml:lang="">
+<head>
+  <meta charset="utf-8" />
+  <meta name="generator" content="pandoc" />
+  <meta name="viewport" content="width=device-width, initial-scale=1.0, user-scalable=yes" />
+  <title>demo</title>
+  <style>
+    code{white-space: pre-wrap;}
+    span.smallcaps{font-variant: small-caps;}
+    span.underline{text-decoration: underline;}
+    div.column{display: inline-block; vertical-align: top; width: 50%;}
+    div.hanging-indent{margin-left: 1.5em; text-indent: -1.5em;}
+    ul.task-list{list-style: none;}
+  </style>
+  <!--[if lt IE 9]>
+    <script src="//cdnjs.cloudflare.com/ajax/libs/html5shiv/3.7.3/html5shiv-printshiv.min.js"></script>
+  <![endif]-->
+</head>
+<body>
+<h1 id="iscc-test-document">ISCC Test Document</h1>
+<p>Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet.</p>
+<p>Duis autem vel eum iriure dolor in hendrerit in vulputate velit esse molestie consequat, vel illum dolore eu feugiat nulla facilisis at vero eros et accumsan et iusto odio dignissim qui blandit praesent luptatum zzril delenit augue duis dolore te feugait nulla facilisi. Lorem ipsum dolor sit amet, consectetuer adipiscing elit, sed diam nonummy nibh euismod tincidunt ut laoreet dolore magna aliquam erat volutpat.</p>
+<p>Ut wisi enim ad minim veniam, quis nostrud exerci tation ullamcorper suscipit lobortis nisl ut aliquip ex ea commodo consequat. Duis autem vel eum iriure dolor in hendrerit in vulputate velit esse molestie consequat, vel illum dolore eu feugiat nulla facilisis at vero eros et accumsan et iusto odio dignissim qui blandit praesent luptatum zzril delenit augue duis dolore te feugait nulla facilisi.</p>
+<p>Nam liber tempor cum soluta nobis eleifend option congue nihil imperdiet doming id quod mazim placerat facer possim assum. Lorem ipsum dolor sit amet, consectetuer adipiscing elit, sed diam nonummy nibh euismod tincidunt ut laoreet dolore magna aliquam erat volutpat. Ut wisi enim ad minim veniam, quis nostrud exerci tation ullamcorper suscipit lobortis nisl ut aliquip ex ea commodo consequat.</p>
+<p>Duis autem vel eum iriure dolor in hendrerit in vulputate velit esse molestie consequat, vel illum dolore eu feugiat nulla facilisis.</p>
+<p>At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, At accusam aliquyam diam diam dolore dolores duo eirmod eos erat, et nonumy sed tempor et et invidunt justo labore Stet clita ea et gubergren, kasd magna no rebum. sanctus sea sed takimata ut vero voluptua. est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat.</p>
+<p>Consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus.</p>
+<p>Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet.</p>
+<p>Duis autem vel eum iriure dolor in hendrerit in vulputate velit esse molestie consequat, vel illum dolore eu feugiat nulla facilisis at vero eros et accumsan et iusto odio dignissim qui blandit praesent luptatum zzril delenit augue duis dolore te feugait nulla facilisi. Lorem ipsum dolor sit amet, consectetuer adipiscing elit, sed diam nonummy nibh euismod tincidunt ut laoreet dolore magna aliquam erat volutpat.</p>
+<p>Ut wisi enim ad minim veniam, quis nostrud exerci tation ullamcorper suscipit lobortis nisl ut aliquip ex ea commodo consequat. Duis autem vel eum iriure dolor in hendrerit in vulputate velit esse molestie consequat, vel illum dolore eu feugiat nulla facilisis at vero eros et accumsan et iusto odio dignissim qui blandit praesent luptatum zzril delenit augue duis dolore te feugait nulla facilisi.</p>
+<p>Nam liber tempor cum soluta nobis eleifend option congue nihil imperdiet doming id quod mazim placerat facer possim assum. Lorem ipsum dolor sit amet, consectetuer adipiscing elit, sed diam nonummy nibh euismod tincidunt ut laoreet dolore magna aliquam erat volutpat. Ut wisi enim ad minim veniam, quis nostrud exerci tation ullamcorper suscipit lobortis nisl ut aliquip ex ea commodo consequat.</p>
+</body>
+</html>