Improve copyright detection more

Empty lines can stop a notice continuity.

Signed-off-by: Philippe Ombredanne <pombredanne@nexb.com>

Author: pombredanne

src/cluecode/copyrights.py

@@ -1357,11 +1357,18 @@ def build_detection_from_node(
     (r'^EXHIBIT$', 'JUNK'),
     (r'^Exhibit$', 'JUNK'),
     (r'^Digitized', 'NN'),
+    (r'^OPENING', 'JUNK'),
     (r'^[Ds]istributed?.?$', 'NN'),
     (r'^Distributions?', 'NN'),
     (r'^Multiply$', 'NN'),
     (r'^Convert$', 'NN'),
     (r'^Compute$', 'NN'),
+
+    (r'^\(Computer$', 'JUNK'),
+    (r'^Programs\)', 'JUNK'),
+    (r'^Regulations', 'JUNK'),
+    (r'^message\.', 'JUNK'),
+
     (r'^Case$', 'NN'),
     (r'^Hessian$', 'NN'),
     (r'^Include', 'NN'),
@@ -1434,6 +1441,10 @@ def build_detection_from_node(
     (r'^IA64$', 'NN'),
     (r'^IDEA$', 'NN'),
     (r'^Id$', 'NN'),
+
+    # micapitalized last name 
+    (r'^king$', 'NNP'),
+
     (r'^IDENTIFICATION?\.?$', 'NN'),
     (r'^IEEE$', 'NN'),
     (r'^If$', 'NN'),
@@ -1444,6 +1455,8 @@ def build_detection_from_node(
     (r'^INCLUDING', 'NN'),
     (r'^Indemnification', 'NN'),
     (r'^Indemnified', 'NN'),
+    (r'^Unified$', 'NN'),
+    (r'^Cleaned$', 'JUNK'),
     (r'^Information', 'NN'),
     (r'^In$', 'NN'),
     (r'^Intellij$', 'NN'),
@@ -1540,7 +1553,7 @@ def build_detection_from_node(
     (r'^[Rr]espective', 'NN'),
     (r'^SAX$', 'NN'),
     (r'^Sections?$', 'NN'),
-    (r'^Send$', 'NN'),
+    (r'^Send$', 'JUNK'),
     (r'^Separa', 'NN'),
     (r'^Service$', 'NN'),
     (r'^Several$', 'NN'),
@@ -2160,7 +2173,8 @@ def build_detection_from_node(
     # a .sh shell scripts is NOT an email.
     (r'^.*\.sh\.?$', 'JUNK'),
     # email eventually in parens or brackets with some trailing punct. Note the @ or "at "
-    (r'^[\<\(]?[a-zA-Z0-9]+[a-zA-Z0-9\+_\-\.\%]*(@|at)[a-zA-Z0-9][a-zA-Z0-9\+_\-\.\%]+\.[a-zA-Z]{2,3}[\>\)\.\,]*$', 'EMAIL'),
+    (r'^(?:[A-Za-z])*[\<\(]?[a-zA-Z0-9]+[a-zA-Z0-9\+_\-\.\%]*(@|at)[a-zA-Z0-9][a-zA-Z0-9\+_\-\.\%]+\.[a-zA-Z]{2,3}[\>\)\.\,]*$', 'EMAIL'),
+
     # mailto URLs
     (r'^mailto:.{2,}@.{2,}\.[a-z]{2,3}', 'EMAIL'),
 
@@ -2902,6 +2916,9 @@ def build_detection_from_node(
     # Copyright 2018 (c) DistributedLock
     COPYRIGHT: {<COPY> <YR-RANGE> <COPY>  <NNP>}        #230020
 
+    #  Copyright (C) 1999-2000 VA Linux Systems
+    COPYRIGHT: {<COPY>  <COPY>  <YR-RANGE>  <CAPS>  <NN>  <NNP>} #2280-1
+
     COPYRIGHT2: {<COPY>+ <NN|CAPS>? <YR-RANGE>+ <PN>*}        #2280
 
     # using #2280 above: Copyright 2018 Developers of the Rand project
@@ -3043,6 +3060,9 @@ def build_detection_from_node(
     #Copyright or Copr. CNRS
     NAME-CAPS: {<CAPS>+}        #2530
 
+    # (C) SGI 2006, Christoph Lameter
+    COPYRIGHT: {<COPY>  <NAME-CAPS>  <NAME-YEAR> } #25501
+
     #Copyright or Copr. CNRS
     COPYRIGHT: {<COPY> <NN> <COPY> <COPYRIGHT|NAME-CAPS>}        #2560
     COPYRIGHT: {<COPYRIGHT2> <BY> <NAME-CAPS>} #2561

src/licensedcode/data/licenses/maxmind-geolite2-eula-2019.LICENSE

@@ -10,7 +10,7 @@ ignorable_authors:
     - the USA Department of Commerce
     - the USA Department of State. Specifically
     - the USA Treasury Department's Office of Foreign Assets Control, and the International
-        Traffic in Arms Regulations
+        Traffic in Arms
 ignorable_urls:
     - http://www.maxmind.com/
     - https://www.maxmind.com/
@@ -114,4 +114,4 @@ Should any provision of this Agreement be held void, invalid, or inoperative, su
 
 COMPLIANCE WITH LAW.
 
-Notwithstanding any provisions of this Agreement to the contrary, you shall in performance of this Agreement comply with all applicable laws, executive orders, regulations ordinances and rules of all governments (“Applicable Laws”), including all applicable export and re-export control laws and regulations, such as the Export Administration Regulations (“EAR”) maintained by the USA Department of Commerce, trade and economic sanctions maintained by the USA Treasury Department’s Office of Foreign Assets Control, and the International Traffic in Arms Regulations (“ITAR”) maintained by the USA Department of State.  Specifically, and without limitation, you agree that you shall not, directly or indirectly, sell, export, re-export, transfer, divert, or otherwise dispose of any Services (including products derived from or based on such Services) to any destination, entity, or person prohibited by the laws or regulations of the USA, without obtaining prior authorization from the competent government authorities as required by those laws and regulations.
+Notwithstanding any provisions of this Agreement to the contrary, you shall in performance of this Agreement comply with all applicable laws, executive orders, regulations ordinances and rules of all governments (“Applicable Laws”), including all applicable export and re-export control laws and regulations, such as the Export Administration Regulations (“EAR”) maintained by the USA Department of Commerce, trade and economic sanctions maintained by the USA Treasury Department’s Office of Foreign Assets Control, and the International Traffic in Arms Regulations (“ITAR”) maintained by the USA Department of State.  Specifically, and without limitation, you agree that you shall not, directly or indirectly, sell, export, re-export, transfer, divert, or otherwise dispose of any Services (including products derived from or based on such Services) to any destination, entity, or person prohibited by the laws or regulations of the USA, without obtaining prior authorization from the competent government authorities as required by those laws and regulations.

tests/cluecode/data/copyrights/misco4/linux2/designer.txt.yml

@@ -3,6 +3,6 @@ what:
   - holders
   - authors
 copyrights:
-  - Copyright (c) IBM Corporation, 2011-2015
+  - Copyright (c) IBM Corporation, 2011-2015 Designer of the Power
 holders:
-  - IBM Corporation
+  - IBM Corporation, Designer of the Power

tests/cluecode/data/copyrights/misco4/linux4/BY.txt

@@ -0,0 +1 @@
+MediaTek Inc. (c) 2008 BY OPENING

tests/cluecode/data/copyrights/misco4/linux4/BY.txt.yml

@@ -0,0 +1,8 @@
+what:
+  - copyrights
+  - holders
+  - authors
+copyrights:
+  - MediaTek Inc. (c) 2008
+holders:
+  - MediaTek Inc.

tests/cluecode/data/copyrights/misco4/linux4/capture.txt

@@ -0,0 +1,6 @@
+ 0.0.16
+   Modified Copyright message.
+ 0.0.17
+   Implement Mic and Line in Capture.
+ 0.0.18
+

tests/cluecode/data/copyrights/misco4/linux4/capture.txt.yml

@@ -0,0 +1,4 @@
+what:
+  - copyrights
+  - holders
+  - authors

tests/cluecode/data/copyrights/misco4/linux4/dev-by.txt

@@ -0,0 +1,4 @@
+Developed by:
+
+    LLVM Team
+

tests/cluecode/data/copyrights/misco4/linux4/dev-by.txt.yml

@@ -0,0 +1,6 @@
+what:
+  - copyrights
+  - holders
+  - authors
+authors:
+  - LLVM Team

tests/cluecode/data/copyrights/misco4/linux4/king.txt

@@ -0,0 +1,2 @@
+*  Copyright (C) 1997-2002 Russell king
+