Fix binary gibberish bug on extra newlines

Regen test expectations for this and also fix another test.

Signed-off-by: Ayan Sinha Mahapatra <ayansmahapatra@gmail.com>

Author: AyanSinhaMahapatra

src/licensedcode/models.py

@@ -463,7 +463,7 @@ def load(self, license_file, check_consistency=True):
 
                 self.text = ''
             else:
-                self.text = post.content
+                self.text = post.content.lstrip()
 
             for k, v in data.items():
                 if k == 'minimum_coverage':
@@ -1927,7 +1927,7 @@ def load(self, rule_file, with_checks=True):
                     f'{self}: file://{rule_file}'
                 )
 
-            self.text = post.content
+            self.text = post.content.lstrip()
 
         except Exception as e:
             print('#############################')

tests/licensedcode/data/license_db/index.json-expected.json

@@ -11,4 +11,4 @@ text_urls:
     - https://git.savannah.gnu.org/cgit/bash.git/plain/COPYING?h=bash-3.0-rc1&id=dd9e6dfa23d0dae4888f11fb8c6a27bc36d1b283
 ---
 
-b'\nThe Free Software Foundation has exempted Bash from the requirement of\nParagraph 2c of the General Public License.  This is to say, there is\nno requirement for Bash to print a notice when it is started\ninteractively in the usual way.  We made this exception because users\nand standards expect shells not to print such messages.  This\nexception applies to any program that serves as a shell and that is\nbased primarily on Bash as opposed to other GNU software.'
+b'The Free Software Foundation has exempted Bash from the requirement of\nParagraph 2c of the General Public License.  This is to say, there is\nno requirement for Bash to print a notice when it is started\ninteractively in the usual way.  We made this exception because users\nand standards expect shells not to print such messages.  This\nexception applies to any program that serves as a shell and that is\nbased primarily on Bash as opposed to other GNU software.'

tests/licensedcode/data/license_db/license_dump/bash-exception-gpl.LICENSE

@@ -132,8 +132,7 @@
         <dt style="">text</dt>
         <dd>
 
-            
-The Free Software Foundation has exempted Bash from the requirement of
+            The Free Software Foundation has exempted Bash from the requirement of
 Paragraph 2c of the General Public License.  This is to say, there is
 no requirement for Bash to print a notice when it is started
 interactively in the usual way.  We made this exception because users
@@ -145,8 +144,7 @@
 
     </dl>
     <div class="text-bold">license_text</div>
-    <pre id="license-text" class="code mt-1" style="white-space: pre-wrap;"><code>
-The Free Software Foundation has exempted Bash from the requirement of
+    <pre id="license-text" class="code mt-1" style="white-space: pre-wrap;"><code>The Free Software Foundation has exempted Bash from the requirement of
 Paragraph 2c of the General Public License.  This is to say, there is
 no requirement for Bash to print a notice when it is started
 interactively in the usual way.  We made this exception because users
@@ -164,7 +162,7 @@
       <a href="https://www.aboutcode.org/" target="_blank">AboutCode</a>
     </p>
     <p>Designed and built by <a href="https://www.nexb.com/" target="_blank">nexB</a>. Licensed under the <a href="cc-by-4.0.html">Creative Commons Attribution License 4.0 (CC-BY-4.0)</a>.</p>
-    <p>Generated with <a href="https://github.com/nexB/scancode-toolkit" target="_blank">ScanCode toolkit</a> 31.1.0 on Sep 28, 2022.</p>
+    <p>Generated with <a href="https://github.com/nexB/scancode-toolkit" target="_blank">ScanCode toolkit</a> 31.2.1 on Oct 14, 2022.</p>
   </footer>
 </div>
 

tests/licensedcode/data/license_db/license_dump/bash-exception-gpl.html

@@ -10,5 +10,5 @@
   "text_urls": [
     "https://git.savannah.gnu.org/cgit/bash.git/plain/COPYING?h=bash-3.0-rc1&id=dd9e6dfa23d0dae4888f11fb8c6a27bc36d1b283"
   ],
-  "text": "\nThe Free Software Foundation has exempted Bash from the requirement of\nParagraph 2c of the General Public License.  This is to say, there is\nno requirement for Bash to print a notice when it is started\ninteractively in the usual way.  We made this exception because users\nand standards expect shells not to print such messages.  This\nexception applies to any program that serves as a shell and that is\nbased primarily on Bash as opposed to other GNU software."
+  "text": "The Free Software Foundation has exempted Bash from the requirement of\nParagraph 2c of the General Public License.  This is to say, there is\nno requirement for Bash to print a notice when it is started\ninteractively in the usual way.  We made this exception because users\nand standards expect shells not to print such messages.  This\nexception applies to any program that serves as a shell and that is\nbased primarily on Bash as opposed to other GNU software."
 }

tests/licensedcode/data/license_db/license_dump/bash-exception-gpl.json

@@ -9,7 +9,6 @@ spdx_license_key: LicenseRef-scancode-bash-exception-gpl-2.0
 text_urls:
   - https://git.savannah.gnu.org/cgit/bash.git/plain/COPYING?h=bash-3.0-rc1&id=dd9e6dfa23d0dae4888f11fb8c6a27bc36d1b283
 text: |
-
   The Free Software Foundation has exempted Bash from the requirement of
   Paragraph 2c of the General Public License.  This is to say, there is
   no requirement for Bash to print a notice when it is started

tests/licensedcode/data/license_db/license_dump/bash-exception-gpl.yml

@@ -8,4 +8,4 @@ homepage_url: https://git.kernel.org/pub/scm/linux/kernel/git/firmware/linux-fir
 spdx_license_key: LicenseRef-scancode-binary-linux-firmware
 ---
 
-b'\nRedistribution. Redistribution and use in binary form, without\nmodification, are permitted provided that the following conditions are\nmet:\n\n* Redistributions must reproduce the above copyright notice and the\nfollowing disclaimer in the documentation and/or other materials\nprovided with the distribution.\n\n* Neither the name of the Copyright Holder nor the names of its\nsuppliers may be used to endorse or promote products derived from this\nsoftware without specific prior written permission.\n\n* No reverse engineering, decompilation, or disassembly of this software\nis permitted.\n\nDISCLAIMER. THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND\nCONTRIBUTORS "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING,\nBUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND\nFITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE\nCOPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,\nINCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT\nNOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF\nUSE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON\nANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT\n(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF\nTHIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE'
+b'Redistribution. Redistribution and use in binary form, without\nmodification, are permitted provided that the following conditions are\nmet:\n\n* Redistributions must reproduce the above copyright notice and the\nfollowing disclaimer in the documentation and/or other materials\nprovided with the distribution.\n\n* Neither the name of the Copyright Holder nor the names of its\nsuppliers may be used to endorse or promote products derived from this\nsoftware without specific prior written permission.\n\n* No reverse engineering, decompilation, or disassembly of this software\nis permitted.\n\nDISCLAIMER. THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND\nCONTRIBUTORS "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING,\nBUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND\nFITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE\nCOPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,\nINCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT\nNOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF\nUSE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON\nANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT\n(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF\nTHIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE'

tests/licensedcode/data/license_db/license_dump/binary-linux-firmware.LICENSE

@@ -116,8 +116,7 @@
         <dt style="">text</dt>
         <dd>
 
-            
-Redistribution. Redistribution and use in binary form, without
+            Redistribution. Redistribution and use in binary form, without
 modification, are permitted provided that the following conditions are
 met:
 
@@ -148,8 +147,7 @@
 
     </dl>
     <div class="text-bold">license_text</div>
-    <pre id="license-text" class="code mt-1" style="white-space: pre-wrap;"><code>
-Redistribution. Redistribution and use in binary form, without
+    <pre id="license-text" class="code mt-1" style="white-space: pre-wrap;"><code>Redistribution. Redistribution and use in binary form, without
 modification, are permitted provided that the following conditions are
 met:
 
@@ -186,7 +184,7 @@
       <a href="https://www.aboutcode.org/" target="_blank">AboutCode</a>
     </p>
     <p>Designed and built by <a href="https://www.nexb.com/" target="_blank">nexB</a>. Licensed under the <a href="cc-by-4.0.html">Creative Commons Attribution License 4.0 (CC-BY-4.0)</a>.</p>
-    <p>Generated with <a href="https://github.com/nexB/scancode-toolkit" target="_blank">ScanCode toolkit</a> 31.1.0 on Sep 28, 2022.</p>
+    <p>Generated with <a href="https://github.com/nexB/scancode-toolkit" target="_blank">ScanCode toolkit</a> 31.2.1 on Oct 14, 2022.</p>
   </footer>
 </div>
 

tests/licensedcode/data/license_db/license_dump/binary-linux-firmware.html

@@ -6,5 +6,5 @@
   "owner": "Unspecified",
   "homepage_url": "https://git.kernel.org/pub/scm/linux/kernel/git/firmware/linux-firmware.git/tree/",
   "spdx_license_key": "LicenseRef-scancode-binary-linux-firmware",
-  "text": "\nRedistribution. Redistribution and use in binary form, without\nmodification, are permitted provided that the following conditions are\nmet:\n\n* Redistributions must reproduce the above copyright notice and the\nfollowing disclaimer in the documentation and/or other materials\nprovided with the distribution.\n\n* Neither the name of the Copyright Holder nor the names of its\nsuppliers may be used to endorse or promote products derived from this\nsoftware without specific prior written permission.\n\n* No reverse engineering, decompilation, or disassembly of this software\nis permitted.\n\nDISCLAIMER. THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND\nCONTRIBUTORS \"AS IS\" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING,\nBUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND\nFITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE\nCOPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,\nINCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT\nNOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF\nUSE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON\nANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT\n(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF\nTHIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE"
+  "text": "Redistribution. Redistribution and use in binary form, without\nmodification, are permitted provided that the following conditions are\nmet:\n\n* Redistributions must reproduce the above copyright notice and the\nfollowing disclaimer in the documentation and/or other materials\nprovided with the distribution.\n\n* Neither the name of the Copyright Holder nor the names of its\nsuppliers may be used to endorse or promote products derived from this\nsoftware without specific prior written permission.\n\n* No reverse engineering, decompilation, or disassembly of this software\nis permitted.\n\nDISCLAIMER. THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND\nCONTRIBUTORS \"AS IS\" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING,\nBUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND\nFITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE\nCOPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,\nINCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT\nNOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF\nUSE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON\nANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT\n(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF\nTHIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE"
 }

tests/licensedcode/data/license_db/license_dump/binary-linux-firmware.json

@@ -6,7 +6,6 @@ owner: Unspecified
 homepage_url: https://git.kernel.org/pub/scm/linux/kernel/git/firmware/linux-firmware.git/tree/
 spdx_license_key: LicenseRef-scancode-binary-linux-firmware
 text: |
-
   Redistribution. Redistribution and use in binary form, without
   modification, are permitted provided that the following conditions are
   met: