Add sanity check for non-ASCII character and trailing spaces (#927)

* add CI sanity check for non-ASCII encoding and trailing spaces

* check TAB too

* fix ordering

* rename sanity to sanitycheck

.github/workflows/sanitycheck.yml

@@ -1,11 +1,11 @@
-name: spellcheck
+name: sanitycheck
 
 on:
   pull_request:
     branches: [ master ]
 
 jobs:
-  build:
+  misspell:
     runs-on: ubuntu-latest
 
     steps:
@@ -19,3 +19,13 @@ jobs:
 
     - name: run misspell
       run: ./bin/misspell -error .
+
+  encoding:
+    runs-on: ubuntu-latest
+
+    steps:
+    - name: check out code
+      uses: actions/checkout@v2
+
+    - name: detect non-ASCII encoding and trailing space
+      run: python3 ./build/sanitycheck.py

build/sanitycheck.py

@@ -0,0 +1,45 @@
+#!/usr/bin/env python3
+
+import glob
+import os
+import sys
+
+def sanitycheck(pattern, allow_utf8 = False):
+    error_count = 0
+
+    for filename in glob.glob(pattern, recursive=True):
+        if not os.path.isfile(filename):
+            continue
+        with open(filename, 'rb') as file:
+            content = file.read()
+            error = []
+            lineno = 1
+            for line in content.splitlines():
+                if allow_utf8 and lineno == 1 and line.startswith(b'\xef\xbb\xbf'):
+                    line = line[3:]
+                if any(b > 127 for b in line):
+                    error.append('  Non-ASCII character found at Ln:{} {}'.format(lineno, line))
+                if line[-1:] == b' ' or line[-1:] == b'\t':
+                    error.append('  Trailing space found at Ln:{} {}'.format(lineno, line))
+                lineno += 1
+            if error:
+                error_count += 1
+                print('{} [FAIL]'.format(filename), file=sys.stderr)
+                for msg in error:
+                    print(msg, file=sys.stderr)
+            else:
+                # print('{} [PASS]'.format(filename))
+                pass
+
+    return error_count
+
+retval = 0
+retval += sanitycheck('**/*.cmd')
+retval += sanitycheck('**/*.cs', allow_utf8 = True)
+retval += sanitycheck('**/*.csproj', allow_utf8 = True)
+retval += sanitycheck('**/*.md')
+retval += sanitycheck('**/*.proj', allow_utf8 = True)
+retval += sanitycheck('**/*.py')
+retval += sanitycheck('**/*.xml', allow_utf8 = True)
+
+sys.exit(retval)

examples/AspNet/Properties/AssemblyInfo.cs

@@ -9,7 +9,7 @@ using System.Runtime.InteropServices;
 [assembly: AssemblyConfiguration("")]
 [assembly: AssemblyCompany("")]
 [assembly: AssemblyProduct("Examples.AspNet")]
-[assembly: AssemblyCopyright("Copyright ©  2020")]
+[assembly: AssemblyCopyright("Copyright @ 2020")]
 [assembly: AssemblyTrademark("")]
 [assembly: AssemblyCulture("")]
 

src/OpenTelemetry.Exporter.Jaeger/ApacheThrift/README.md

@@ -1,4 +1,4 @@
-# Open Telemetry - Jaeger Exporter - Apache Thrift
+# Open Telemetry - Jaeger Exporter - Apache Thrift
 
 This folder contains a stripped-down fork of the [ApacheThrift
 0.13.0.1](https://www.nuget.org/packages/ApacheThrift/0.13.0.1) library from

src/OpenTelemetry.Exporter.OpenTelemetryProtocol/Implementation/README.md

@@ -1,4 +1,4 @@
-# OpenTelemetry Protocol Implementation
+# OpenTelemetry Protocol Implementation
 
 `.proto` files under `Implementation\` are copied from the
 [`opentelemetry-proto`](https://github.com/open-telemetry/opentelemetry-proto/commit/1a931b4b57c34e7fd8f7dddcaa9b7587840e9c08)

src/OpenTelemetry.Exporter.OpenTelemetryProtocol/README.md

@@ -35,4 +35,3 @@ for an example of how to use the exporter.
 * [OpenTelemetry Project](https://opentelemetry.io/)
 * [OpenTelemetry
   Protocol](https://github.com/open-telemetry/opentelemetry-proto)
-  

test/Benchmarks/README.md

@@ -1,4 +1,4 @@
-# OpenTelemetry Benchmarks
+# OpenTelemetry Benchmarks
 
 Use the following example to run Benchmarks from command line:
 (change parameters as necessary)