Merge branch 'unicode'

6 files changed, 38 insertions, 0 deletions

diff --git a/tests/unicode/data/utf-8_1.txt b/tests/unicode/data/utf-8_1.txt
new file mode 100644
index 000000000..d84c480d1
--- /dev/null
+++ b/tests/unicode/data/utf-8_1.txt
@@ -0,0 +1 @@
+Привет
diff --git a/tests/unicode/file1.py b/tests/unicode/file1.py
new file mode 100644
index 000000000..554e88674
--- /dev/null
+++ b/tests/unicode/file1.py
@@ -0,0 +1,4 @@
+f = open("unicode/data/utf-8_1.txt")
+l = f.readline()
+print(l)
+print(len(l))
diff --git a/tests/unicode/unicode.py b/tests/unicode/unicode.py
new file mode 100644
index 000000000..c7e523f06
--- /dev/null
+++ b/tests/unicode/unicode.py
@@ -0,0 +1,18 @@
+# Test a UTF-8 encoded literal
+s = "asdf©qwer"
+for i in range(len(s)):
+    print("s[%d]: %s   %X"%(i, s[i], ord(s[i])))
+
+# Test all three forms of Unicode escape, and
+# all blocks of UTF-8 byte patterns
+s = "a\xA9\xFF\u0123\u0800\uFFEE\U0001F44C"
+for i in range(-len(s), len(s)):
+    print("s[%d]: %s   %X"%(i, s[i], ord(s[i])))
+    print("s[:%d]: %d chars, '%s'"%(i, len(s[:i]), s[:i]))
+    for j in range(i, len(s)):
+        print("s[%d:%d]: %d chars, '%s'"%(i, j, len(s[i:j]), s[i:j]))
+    print("s[%d:]: %d chars, '%s'"%(i, len(s[i:]), s[i:]))
+
+# Test UTF-8 encode and decode
+enc = s.encode()
+print(enc, enc.decode() == s)
diff --git a/tests/unicode/unicode_index.py b/tests/unicode/unicode_index.py
new file mode 100644
index 000000000..3c31468a4
--- /dev/null
+++ b/tests/unicode/unicode_index.py
@@ -0,0 +1,6 @@
+print("Привет".find("т"))
+print("Привет".find("П"))
+print("Привет".rfind("т"))
+print("Привет".rfind("П"))
+print("Привет".index("т"))
+print("Привет".index("П"))
diff --git a/tests/unicode/unicode_iter.py b/tests/unicode/unicode_iter.py
new file mode 100644
index 000000000..f08a4acee
--- /dev/null
+++ b/tests/unicode/unicode_iter.py
@@ -0,0 +1,4 @@
+for c in "Hello":
+    print(c)
+for c in "Привет":
+    print(c)
diff --git a/tests/unicode/unicode_pos.py b/tests/unicode/unicode_pos.py
new file mode 100644
index 000000000..6a5982920
--- /dev/null
+++ b/tests/unicode/unicode_pos.py
@@ -0,0 +1,5 @@
+# str methods with explicit start/end pos
+print("Привет".startswith("П"))
+print("Привет".startswith("р", 1))
+print("абвба".find("а", 1))
+print("абвба".find("а", 1, -1))