micropython: add micropython component

components/language/micropython/tests/unicode/data/utf-8_1.txt

@@ -0,0 +1 @@
+Привет

components/language/micropython/tests/unicode/data/utf-8_2.txt

@@ -0,0 +1,2 @@
+aαbβcγdδ
+ぁ🙐

components/language/micropython/tests/unicode/file1.py

@@ -0,0 +1,4 @@
+f = open("unicode/data/utf-8_1.txt", encoding="utf-8")
+l = f.readline()
+print(l)
+print(len(l))

components/language/micropython/tests/unicode/file2.py

@@ -0,0 +1,28 @@
+# test reading a given number of characters
+
+
+def do(mode):
+    if mode == "rb":
+        enc = None
+    else:
+        enc = "utf-8"
+    f = open("unicode/data/utf-8_2.txt", mode=mode, encoding=enc)
+    print(f.read(1))
+    print(f.read(1))
+    print(f.read(2))
+    print(f.read(4))
+
+    # skip to end of line
+    f.readline()
+
+    # check 3-byte utf-8 char
+    print(f.read(1 if mode == "rt" else 3))
+
+    # check 4-byte utf-8 char
+    print(f.read(1 if mode == "rt" else 4))
+
+    f.close()
+
+
+do("rb")
+do("rt")

components/language/micropython/tests/unicode/unicode.py

@@ -0,0 +1,53 @@
+# 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)
+
+# printing of unicode chars using repr
+# NOTE: for some characters (eg \u10ff) we differ to CPython
+print(repr("a\uffff"))
+print(repr("a\U0001ffff"))
+
+# test invalid escape code
+try:
+    eval('"\\U00110000"')
+except SyntaxError:
+    print("SyntaxError")
+
+# test unicode string given to int
+try:
+    int("\u0200")
+except ValueError:
+    print("ValueError")
+
+# test invalid UTF-8 string
+try:
+    str(b"ab\xa1", "utf8")
+except UnicodeError:
+    print("UnicodeError")
+try:
+    str(b"ab\xf8", "utf8")
+except UnicodeError:
+    print("UnicodeError")
+try:
+    str(bytearray(b"ab\xc0a"), "utf8")
+except UnicodeError:
+    print("UnicodeError")
+try:
+    str(b"\xf0\xe0\xed\xe8", "utf8")
+except UnicodeError:
+    print("UnicodeError")

components/language/micropython/tests/unicode/unicode_chr.py

@@ -0,0 +1,5 @@
+# test builtin chr with unicode characters
+
+print(chr(945))
+print(chr(0x800))
+print(chr(0x10000))

components/language/micropython/tests/unicode/unicode_id.py

@@ -0,0 +1,32 @@
+# test unicode in identifiers
+
+# comment
+# αβγδϵφζ
+
+# global identifiers
+α = 1
+αβγ = 2
+bβ = 3
+βb = 4
+print(α, αβγ, bβ, βb)
+
+# function, argument, local identifiers
+def α(β, γ):
+    δ = β + γ
+    print(β, γ, δ)
+
+
+α(1, 2)
+
+# class, method identifiers
+class φ:
+    def __init__(self):
+        pass
+
+    def δ(self, ϵ):
+        print(ϵ)
+
+
+zζzζz = φ()
+if hasattr(zζzζz, "δ"):
+    zζzζz.δ(ϵ=123)

components/language/micropython/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"))

components/language/micropython/tests/unicode/unicode_iter.py

@@ -0,0 +1,4 @@
+for c in "Hello":
+    print(c)
+for c in "Привет":
+    print(c)

components/language/micropython/tests/unicode/unicode_ord.py

@@ -0,0 +1,3 @@
+# test builtin ord with unicode characters
+
+print(ord("α"))

components/language/micropython/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))

components/language/micropython/tests/unicode/unicode_slice.py

@@ -0,0 +1,12 @@
+# Test slicing of Unicode strings
+
+s = "Привет"
+
+print(s[:])
+print(s[2:])
+print(s[:5])
+print(s[2:5])
+print(s[2:5:1])
+print(s[2:10])
+print(s[-3:10])
+print(s[-4:10])

components/language/micropython/tests/unicode/unicode_str_format.py

@@ -0,0 +1,4 @@
+# test handling of unicode chars in format strings
+
+print("α".format())
+print("{α}".format(α=1))

components/language/micropython/tests/unicode/unicode_str_modulo.py

@@ -0,0 +1,3 @@
+# test handling of unicode chars in string % formatting
+
+print("α" % ())

components/language/micropython/tests/unicode/unicode_subscr.py

@@ -0,0 +1,23 @@
+a = "¢пр"
+
+print(a[0], a[0:1])
+print(a[1], a[1:2])
+print(a[2], a[2:3])
+try:
+    print(a[3])
+except IndexError:
+    print("IndexError")
+print(a[3:4])
+
+print(a[-1])
+print(a[-2], a[-2:-1])
+print(a[-3], a[-3:-2])
+try:
+    print(a[-4])
+except IndexError:
+    print("IndexError")
+print(a[-4:-3])
+
+print(a[0:2])
+print(a[1:3])
+print(a[2:4])