Merge branch 'release/1.4.0'

fedelemantuano · Jul 24, 2018 · c008f84 · c008f84
2 parents 6c9636c + 24d0596
commit c008f84
Show file tree

Hide file tree

Showing 14 changed files with 330 additions and 180 deletions.
diff --git a/.gitignore b/.gitignore
@@ -6,4 +6,4 @@ MANIFEST
 build/
 dist/
 tika_app.egg-info/
-venv/
+venv*/
diff --git a/.travis.yml b/.travis.yml
@@ -9,7 +9,7 @@ python:
     - "3.6"
 
 env:
-    - TIKA_VER="1.16"
+    - TIKA_VER="1.18"
       TIKA_APP_JAR=/tmp/tika-app-${TIKA_VER}.jar
 
 before_script:
@@ -37,11 +37,21 @@ script:
     - python -m tikapp -v
     - python -m tikapp -h
     - python -m tikapp -a -f tests/files/test.zip
+    - python -m tikapp -a -k < tests/files/test.zip
+
+deploy:
+    provider: pypi
+    user: fmantuano
+    password:
+        secure: "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"
+    on:
+        tags: true
+        branch: master
 
 after_success:
     coveralls
 
 notifications:
     email: false
     slack:
-        secure: gLkkwrBjb0jCuiqMCRM5hXPzYH+LNA5UpMcvjULKtvywVnFVren0UYVyp6h81eQhsvIZecghESTitwRwL7Ttl9/TEmiJ1fuD/pjUbRtUDQourm3zpPAlxppVaj61Hfnln6MyPW+1QIlfXpOJRl+k7RrLKTm0FxXP6TS9t9t+p97ZIVz/iOVGwYWNgeSIdxy6sdzISkMx3i3bn7tr/ILruc18wqbaBs7GzQpgjaFl0S+7PDv4vBmj/9dTYxku6G+nSuzz+Do+BXAMCdcSEn4O4HT+tYyxmkCgRqn7zM8KtAXQwNkuSdjTOZo3Pn917jZibrEj8SaqbfXW1Q2BSN30zTk6p0Y22DF26qbYcy1XX6VDL52oy9GCGth1vNGNkLh/rFQHhZfCXvaSz1jws9vrtbEtHPXaYqfA+p/Xi01N1ewLMaL8yWA9NnCNF9r178bjiKtb7TAWu7B2o2I1j3FqfvtXsQsCQvNGTUc0LFP6i3geS056J8jrtz21IXvUmAJLHY5Qx9j88/lwA2HnhJquY7pFUztjXTgl2JBsBeGgzyoERnhq75iWQATteqbBkW1t5jkivw8g5QNbwln10PQij0SvvV9Cr02W7yX2nXt77/YeHR7ddwxxTNK8xUcjJJGUdB3AAGq1R92G/rEs4WfTniS8wG0CksOqyZ2BF1Q0gdk=
+        secure: "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"
diff --git a/README.md b/README.md
@@ -8,6 +8,12 @@
 ## Overview
 
 tika-app-python is a wrapper for [Apache Tika App](https://tika.apache.org/).
+With this library you can analyze:
+ - file on disk
+ - payload in base64
+ - file object (like standard input)
+
+To use file object function you should use Apache Tika version >= 1.17.
 
 ### Apache 2 Open Source License
 tika-app-python can be downloaded, used, and modified free of charge. It is available under the Apache 2 license.
@@ -48,7 +54,7 @@ Import `TikaApp` class:
 ```
 from tikapp import TikaApp
 
-tika_client = TikaApp(file_jar="/opt/tika/tika-app-1.15.jar")
+tika_client = TikaApp(file_jar="/opt/tika/tika-app-1.18.jar")
 ```
 
 For get **content type**:
@@ -75,7 +81,7 @@ For detect **only content**:
 tika_client.extract_only_content("your_file")
 ```
 
-If you want to use payload in base64, you can use the same methods with `payload` argument:
+You can analyze payload in base64 with the same methods, but passing `payload` argument:
 
 ```
 tika_client.detect_content_type(payload="base64_payload")
@@ -84,6 +90,14 @@ tika_client.extract_all_content(payload="base64_payload")
 tika_client.extract_only_content(payload="base64_payload")
 ```
 
+or you can analyze file object (like standard input) with the same methods, but passing `objectInput` argument:
+
+```
+tika_client.detect_language(objectInput="objectInput")
+tika_client.extract_all_content(objectInput="objectInput")
+tika_client.extract_only_content(objectInput="objectInput")
+```
+
 ## Usage from command-line
 
 If you installed tika-app-python with `pip` or `setup.py` you can use it with command-line.
@@ -97,8 +111,8 @@ The last one overwrite all the others.
 These are all swithes:
 
 ```
-usage: tikapp [-h] (-f FILE | -p PAYLOAD) [-j JAR] [-d] [-t] [-l] [-a]
-                   [-v]
+usage: tikapp [-h] (-f FILE | -p PAYLOAD | -k) [-j JAR] [-d] [-t] [-l]
+                   [-a] [-v]
 
 Wrapper for Apache Tika App.
 
@@ -107,6 +121,7 @@ optional arguments:
   -f FILE, --file FILE  File to submit (default: None)
   -p PAYLOAD, --payload PAYLOAD
                         Base64 payload to submit (default: None)
+  -k, --stdin           Enable parsing from stdin (default: False)
   -j JAR, --jar JAR     Apache Tika app JAR (default: None)
   -d, --detect          Detect document type (default: False)
   -t, --text            Output plain text content (default: False)
@@ -116,12 +131,18 @@ optional arguments:
   -v, --version         show program's version number and exit
 ```
 
-Example:
+Example from file on disk:
 
 ```shell
 $ tikapp -f example_file -a
 ```
 
+Example from standard input
+
+```shell
+$ tikapp -a -k < example_file
+```
+
 ## Performance tests
 
 These are the results of performance tests in [tests](https://github.com/fedelemantuano/tika-app-python/tree/develop/tests) folder:

diff --git a/README.rst b/README.rst
@@ -1,4 +1,8 @@
-|PyPI version| |Build Status| |Coverage Status| |BCH compliance|
+`PyPI version <https://badge.fury.io/py/tika-app>`__ `Build
+Status <https://travis-ci.org/fedelemantuano/tika-app-python>`__
+`Coverage
+Status <https://coveralls.io/github/fedelemantuano/tika-app-python?branch=master>`__
+`BCH compliance <https://bettercodehub.com/>`__
 
 tika-app-python
 ===============
@@ -7,7 +11,10 @@ Overview
 --------
 
 tika-app-python is a wrapper for `Apache Tika
-App <https://tika.apache.org/>`__.
+App <https://tika.apache.org/>`__. With this library you can analyze: -
+file on disk - payload in base64 - file object (like standard input)
+
+To use file object function you should use Apache Tika version >= 1.17.
 
 Apache 2 Open Source License
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~
@@ -31,21 +38,21 @@ Clone repository
 
 ::
 
-    git clone https://github.com/fedelemantuano/tika-app-python.git
+   git clone https://github.com/fedelemantuano/tika-app-python.git
 
 and install tika-app-python with ``setup.py``:
 
 ::
 
-    cd tika-app-python
+   cd tika-app-python
 
-    python setup.py install
+   python setup.py install
 
 or use ``pip``:
 
 ::
 
-    pip install tika-app
+   pip install tika-app
 
 Usage in a project
 ------------------
@@ -54,43 +61,52 @@ Import ``TikaApp`` class:
 
 ::
 
-    from tikapp import TikaApp
+   from tikapp import TikaApp
 
-    tika_client = TikaApp(file_jar="/opt/tika/tika-app-1.15.jar")
+   tika_client = TikaApp(file_jar="/opt/tika/tika-app-1.18.jar")
 
 For get **content type**:
 
 ::
 
-    tika_client.detect_content_type("your_file")
+   tika_client.detect_content_type("your_file")
 
 For detect **language**:
 
 ::
 
-    tika_client.detect_language("your_file")
+   tika_client.detect_language("your_file")
 
 For detect **all metadata and content**:
 
 ::
 
-    tika_client.extract_all_content("your_file")
+   tika_client.extract_all_content("your_file")
 
 For detect **only content**:
 
 ::
 
-    tika_client.extract_only_content("your_file")
+   tika_client.extract_only_content("your_file")
 
-If you want to use payload in base64, you can use the same methods with
+You can analyze payload in base64 with the same methods, but passing
 ``payload`` argument:
 
 ::
 
-    tika_client.detect_content_type(payload="base64_payload")
-    tika_client.detect_language(payload="base64_payload")
-    tika_client.extract_all_content(payload="base64_payload")
-    tika_client.extract_only_content(payload="base64_payload")
+   tika_client.detect_content_type(payload="base64_payload")
+   tika_client.detect_language(payload="base64_payload")
+   tika_client.extract_all_content(payload="base64_payload")
+   tika_client.extract_only_content(payload="base64_payload")
+
+or you can analyze file object (like standard input) with the same
+methods, but passing ``objectInput`` argument:
+
+::
+
+   tika_client.detect_language(objectInput="objectInput")
+   tika_client.extract_all_content(objectInput="objectInput")
+   tika_client.extract_only_content(objectInput="objectInput")
 
 Usage from command-line
 -----------------------
@@ -107,29 +123,36 @@ These are all swithes:
 
 ::
 
-    usage: tikapp [-h] (-f FILE | -p PAYLOAD) [-j JAR] [-d] [-t] [-l] [-a]
-                       [-v]
+   usage: tikapp [-h] (-f FILE | -p PAYLOAD | -k) [-j JAR] [-d] [-t] [-l]
+                      [-a] [-v]
 
-    Wrapper for Apache Tika App.
+   Wrapper for Apache Tika App.
+
+   optional arguments:
+     -h, --help            show this help message and exit
+     -f FILE, --file FILE  File to submit (default: None)
+     -p PAYLOAD, --payload PAYLOAD
+                           Base64 payload to submit (default: None)
+     -k, --stdin           Enable parsing from stdin (default: False)
+     -j JAR, --jar JAR     Apache Tika app JAR (default: None)
+     -d, --detect          Detect document type (default: False)
+     -t, --text            Output plain text content (default: False)
+     -l, --language        Output only language (default: False)
+     -a, --all             Output metadata and content from all embedded files
+                           (default: False)
+     -v, --version         show program's version number and exit
+
+Example from file on disk:
+
+.. code:: shell
 
-    optional arguments:
-      -h, --help            show this help message and exit
-      -f FILE, --file FILE  File to submit (default: None)
-      -p PAYLOAD, --payload PAYLOAD
-                            Base64 payload to submit (default: None)
-      -j JAR, --jar JAR     Apache Tika app JAR (default: None)
-      -d, --detect          Detect document type (default: False)
-      -t, --text            Output plain text content (default: False)
-      -l, --language        Output only language (default: False)
-      -a, --all             Output metadata and content from all embedded files
-                            (default: False)
-      -v, --version         show program's version number and exit
+   $ tikapp -f example_file -a
 
-Example:
+Example from standard input
 
 .. code:: shell
 
-    $ tikapp -f example_file -a
+   $ tikapp -a -k < example_file
 
 Performance tests
 -----------------
@@ -140,25 +163,16 @@ folder:
 
 ::
 
-    (Python 2)
-    tika_content_type()             0.704840 sec
-    tika_detect_language()          1.592066 sec
-    magic_content_type()            0.000215 sec
-    tika_extract_all_content()      0.816366 sec
-    tika_extract_only_content()     0.788667 sec
-
-    (Python 3)
-    tika_content_type()             0.698357 sec
-    tika_detect_language()          1.593452 sec
-    magic_content_type()            0.000226 sec
-    tika_extract_all_content()      0.785915 sec
-    tika_extract_only_content()     0.766517 sec
-
-.. |PyPI version| image:: https://badge.fury.io/py/tika-app.svg
-   :target: https://badge.fury.io/py/tika-app
-.. |Build Status| image:: https://travis-ci.org/fedelemantuano/tika-app-python.svg?branch=master
-   :target: https://travis-ci.org/fedelemantuano/tika-app-python
-.. |Coverage Status| image:: https://coveralls.io/repos/github/fedelemantuano/tika-app-python/badge.svg?branch=master
-   :target: https://coveralls.io/github/fedelemantuano/tika-app-python?branch=master
-.. |BCH compliance| image:: https://bettercodehub.com/edge/badge/fedelemantuano/tika-app-python?branch=develop
-   :target: https://bettercodehub.com/
+   (Python 2)
+   tika_content_type()             0.704840 sec
+   tika_detect_language()          1.592066 sec
+   magic_content_type()            0.000215 sec
+   tika_extract_all_content()      0.816366 sec
+   tika_extract_only_content()     0.788667 sec
+
+   (Python 3)
+   tika_content_type()             0.698357 sec
+   tika_detect_language()          1.593452 sec
+   magic_content_type()            0.000226 sec
+   tika_extract_all_content()      0.785915 sec
+   tika_extract_only_content()     0.766517 sec
diff --git a/requirements.txt b/requirements.txt
@@ -1,4 +1,3 @@
-chainmap
 mail-parser>=3
 python-magic
 simplejson

diff --git a/tests/context.py b/tests/context.py
@@ -0,0 +1,9 @@
+# -*- coding: utf-8 -*-
+
+import sys
+import os
+sys.path.insert(0, os.path.abspath(
+    os.path.join(os.path.dirname(__file__), '..')))
+
+from tikapp import TikaApp
+from tikapp.exceptions import *
diff --git a/tests/files/pdf1.pdf b/tests/files/pdf1.pdf
diff --git a/tests/performance.py b/tests/performance.py
@@ -20,21 +20,18 @@
 from __future__ import unicode_literals
 import magic
 import os
-import sys
 import timeit
 
-profiling_path = os.path.realpath(os.path.dirname(__file__))
-root = os.path.join(profiling_path, '..')
-sys.path.append(root)
-from tikapp import TikaApp
+from context import TikaApp
 
+profiling_path = os.path.realpath(os.path.dirname(__file__))
 test_zip = os.path.join(profiling_path, "files", "lorem_ipsum.txt.zip")
 test_txt = os.path.join(profiling_path, "files", "lorem_ipsum.txt")
 
 try:
     TIKA_APP_JAR = os.environ["TIKA_APP_JAR"]
 except KeyError:
-    TIKA_APP_JAR = "/opt/tika/tika-app-1.15.jar"
+    TIKA_APP_JAR = "/opt/tika/tika-app-1.18.jar"
 
 
 def tika_content_type():