Add office document binary extraction. (#346)

- Add Word Processor DF and binary extraction - Add Spreadsheets DF and binary extraction - Add Presentation Program DF and binary extraction - Add Text files DF and binary extraction - Add tests for new DF and binary extractions - Add test fixtures for new DF and binary extractions - Resolves #303 - Resolves #304 - Resolves #305 - Use aut-resources repo to distribute our shaded tika-parsers 1.22 - Close TikaInputStream - Add RDD filters on MimeTypeTika values - Add CodeCov configuration yaml - Includes work by @jrwiebe, see #346 for all commits before squash
archivesunleashed · Aug 16, 2019 · c824ad814f1c6ebc758597d3ba6bfa57c4c3e43f · c824ad8
1 parent 39831c2
commit c824ad814f1c6ebc758597d3ba6bfa57c4c3e43f
diff --git a/.codecov.yml b/.codecov.yml
@@ -0,0 +1,26 @@
+  
+codecov:
+  
+  notify:
+  
+    require_ci_to_pass: yes
+  
+
+  
+coverage:
+  
+  precision: 2
+  
+  round: down
+  
+  range: "50...80"
+  
+
+  
+  status:
+  
+    project: yes
+  
+    patch: yes
+  
+    changes: no
+  
+
+  
+parsers:
+  
+  gcov:
+  
+    branch_detection:
+  
+      conditional: yes
+  
+      loop: yes
+  
+      method: no
+  
+      macro: no
+  
+
+  
+comment:
+  
+  layout: "header, diff"
+  
+  behavior: default
+  
+  require_changes: no
diff --git a/pom.xml b/pom.xml
@@ -65,6 +65,10 @@
      <id>maven</id>
      <url>http://repo.maven.apache.org/maven2/</url>
    </repository>
+  
+    <repository>
+  
+      <id>mvn-repo</id>
+  
+      <url>https://raw.githubusercontent.com/archivesunleashed/aut-resources/master/mvn-repo</url>
+  
+    </repository>
    <repository>
      <id>jitpack.io</id>
      <url>https://jitpack.io</url>

diff --git a/src/main/scala/io/archivesunleashed/matchbox/DetectMimeTypeTika.scala b/src/main/scala/io/archivesunleashed/matchbox/DetectMimeTypeTika.scala
@@ -38,6 +38,7 @@ object DetectMimeTypeTika {
    } else {
      val tis = TikaInputStream.get(content)
      val mimetype = tika.detect(tis)
+  
+      tis.close()
      mimetype
    }
  }

diff --git a/src/main/scala/io/archivesunleashed/matchbox/ExtractAtMentions.scala b/src/main/scala/io/archivesunleashed/matchbox/ExtractAtMentions.scala