Limit readline()

my_venv/Lib/site-packages/coala_utils/__init__.py

@@ -6,7 +6,7 @@
 
 def get_version():
     with open(VERSION_FILE, 'r') as ver:
-        return ver.readline().strip()
+        return ver.readline(5_000_000).strip()
 
 
 VERSION = get_version()

my_venv/Lib/site-packages/jedi/inference/sys_path.py

@@ -198,7 +198,7 @@ def _get_buildout_script_paths(search_path: Path):
         try:
             filepath = bin_path.joinpath(filename)
             with open(filepath, 'r') as f:
-                firstline = f.readline()
+                firstline = f.readline(5_000_000)
                 if firstline.startswith('#!') and 'python' in firstline:
                     yield filepath
         except (UnicodeDecodeError, IOError) as e:

my_venv/Lib/site-packages/joblib/externals/loky/backend/resource_tracker.py

@@ -234,7 +234,7 @@ def main(fd, verbose=0):
             fd = msvcrt.open_osfhandle(fd, os.O_RDONLY)
         with open(fd, 'rb') as f:
             while True:
-                line = f.readline()
+                line = f.readline(5_000_000)
                 if line == b'':  # EOF
                     break
                 try:

my_venv/Lib/site-packages/nltk/corpus/reader/nkjp.py

@@ -257,7 +257,7 @@ def build_preprocessed_file(self):
             fw = self.write_file
             line = " "
             while len(line):
-                line = fr.readline()
+                line = fr.readline(5_000_000)
                 x = re.split(r"nkjp:[^ ]* ", line)  # in all files
                 ret = " ".join(x)
                 x = re.split("<nkjp:paren>", ret)  # in ann_segmentation.xml

my_venv/Lib/site-packages/nltk/corpus/reader/xmldocs.py

@@ -159,7 +159,7 @@ def _detect_encoding(self, fileid):
                 infile.close()
         else:
             with open(fileid, "rb") as infile:
-                s = infile.readline()
+                s = infile.readline(5_000_000)
         if s.startswith(codecs.BOM_UTF16_BE):
             return "utf-16-be"
         if s.startswith(codecs.BOM_UTF16_LE):

my_venv/Lib/site-packages/numpy/distutils/ccompiler_opt.py

@@ -2578,7 +2578,7 @@ def _generate_config(self, output_dir, dispatch_src, targets, has_baseline=False
         cache_hash = self.cache_hash(targets, has_baseline)
         try:
             with open(config_path) as f:
-                last_hash = f.readline().split("cache_hash:")
+                last_hash = f.readline(5_000_000).split("cache_hash:")
                 if len(last_hash) == 2 and int(last_hash[1]) == cache_hash:
                     return True
         except OSError:

my_venv/Lib/site-packages/numpy/distutils/command/build_src.py

@@ -727,7 +727,7 @@ def swig_sources(self, sources, extension):
 def get_swig_target(source):
     with open(source, 'r') as f:
         result = None
-        line = f.readline()
+        line = f.readline(5_000_000)
         if _has_cpp_header(line):
             result = 'c++'
         if _has_c_header(line):

my_venv/Lib/site-packages/numpy/distutils/fcompiler/__init__.py

@@ -982,7 +982,7 @@ def is_free_format(file):
     # signs of free format are detected.
     result = 0
     with open(file, encoding='latin1') as f:
-        line = f.readline()
+        line = f.readline(5_000_000)
         n = 10000 # the number of non-comment lines to scan for hints
         if _has_f_header(line) or _has_fix_header(line):
             n = 0
@@ -996,12 +996,12 @@ def is_free_format(file):
                 if (line[0]!='\t' and _free_f90_start(line[:5])) or line[-1:]=='&':
                     result = 1
                     break
-            line = f.readline()
+            line = f.readline(5_000_000)
     return result
 
 def has_f90_header(src):
     with open(src, encoding='latin1') as f:
-        line = f.readline()
+        line = f.readline(5_000_000)
     return _has_f90_header(line) or _has_fix_header(line)
 
 _f77flags_re = re.compile(r'(c|)f77flags\s*\(\s*(?P<fcname>\w+)\s*\)\s*=\s*(?P<fflags>.*)', re.I)

my_venv/Lib/site-packages/numpy/f2py/crackfortran.py

@@ -307,7 +307,7 @@ def is_free_format(file):
     # signs of free format are detected.
     result = 0
     with open(file, 'r') as f:
-        line = f.readline()
+        line = f.readline(5_000_000)
         n = 15  # the number of non-comment lines to scan for hints
         if _has_f_header(line):
             n = 0
@@ -320,7 +320,7 @@ def is_free_format(file):
                 if (line[0] != '\t' and _free_f90_start(line[:5])) or line[-2:-1] == '&':
                     result = 1
                     break
-            line = f.readline()
+            line = f.readline(5_000_000)
     return result
 
 

my_venv/Lib/site-packages/numpy/lib/tests/test_format.py

@@ -664,7 +664,7 @@ def test_version_2_0():
 
     # check alignment of data portion
     f.seek(0)
-    header = f.readline()
+    header = f.readline(5_000_000)
     assert_(len(header) % format.ARRAY_ALIGN == 0)
 
     f.seek(0)

my_venv/Lib/site-packages/numpy/random/tests/test_direct.py

@@ -164,7 +164,7 @@ def setup_class(cls):
     @classmethod
     def _read_csv(cls, filename):
         with open(filename) as csv:
-            seed = csv.readline()
+            seed = csv.readline(5_000_000)
             seed = seed.split(',')
             seed = [int(s.strip(), 0) for s in seed[1:]]
             data = []

my_venv/Lib/site-packages/numpy/testing/_private/utils.py

@@ -195,7 +195,7 @@ def memusage(_proc_pid_stat=f'/proc/{os.getpid()}/stat'):
         """
         try:
             with open(_proc_pid_stat, 'r') as f:
-                l = f.readline().split(' ')
+                l = f.readline(5_000_000).split(' ')
             return int(l[22])
         except Exception:
             return
@@ -222,7 +222,7 @@ def jiffies(_proc_pid_stat=f'/proc/{os.getpid()}/stat', _load_time=[]):
             _load_time.append(time.time())
         try:
             with open(_proc_pid_stat, 'r') as f:
-                l = f.readline().split(' ')
+                l = f.readline(5_000_000).split(' ')
             return int(l[13])
         except Exception:
             return int(100*(time.time()-_load_time[0]))

my_venv/Lib/site-packages/pandas/tests/io/parser/common/test_common_basic.py

@@ -938,7 +938,7 @@ def test_read_seek(all_parsers):
     with tm.ensure_clean() as path:
         Path(path).write_text(prefix + content)
         with open(path, encoding="utf-8") as file:
-            file.readline()
+            file.readline(5_000_000)
             actual = parser.read_csv(file)
         expected = parser.read_csv(StringIO(content))
     tm.assert_frame_equal(actual, expected)

my_venv/Lib/site-packages/pip/_internal/operations/install/wheel.py

@@ -99,7 +99,7 @@ def fix_script(path: str) -> bool:
     assert os.path.isfile(path)
 
     with open(path, "rb") as script:
-        firstline = script.readline()
+        firstline = script.readline(5_000_000)
         if not firstline.startswith(b"#!python"):
             return False
         exename = sys.executable.encode(sys.getfilesystemencoding())

my_venv/Lib/site-packages/pip/_internal/req/req_uninstall.py

@@ -530,7 +530,7 @@ def from_dist(cls, dist: BaseDistribution) -> "UninstallPathSet":
             # PEP 660 modern editable is handled in the ``.dist-info`` case
             # above, so this only covers the setuptools-style editable.
             with open(develop_egg_link) as fh:
-                link_pointer = os.path.normcase(fh.readline().strip())
+                link_pointer = os.path.normcase(fh.readline(5_000_000).strip())
                 normalized_link_pointer = normalize_path(link_pointer)
             assert os.path.samefile(
                 normalized_link_pointer, normalized_dist_location

my_venv/Lib/site-packages/pip/_vendor/distlib/scripts.py

@@ -342,7 +342,7 @@ def _copy_script(self, script, filenames):
                 raise
             f = None
         else:
-            first_line = f.readline()
+            first_line = f.readline(5_000_000)
             if not first_line:  # pragma: no cover
                 logger.warning('%s is an empty file (skipping)', script)
                 return

my_venv/Lib/site-packages/pip/_vendor/distro/distro.py

@@ -1294,7 +1294,7 @@ def _parse_distro_release_file(self, filepath: str) -> Dict[str, str]:
             with open(filepath, encoding="utf-8") as fp:
                 # Only parse the first line. For instance, on SLES there
                 # are multiple lines. We don't want them...
-                return self._parse_distro_release_content(fp.readline())
+                return self._parse_distro_release_content(fp.readline(5_000_000))
         except OSError:
             # Ignore not being able to read a specific, seemingly version
             # related file.

my_venv/Lib/site-packages/pythonwin/pywin/Demos/dibdemo.py

@@ -38,15 +38,15 @@ def __init__(self, filename, *bPBM):
         f = open(filename, "rb")
         dib = win32ui.CreateDIBitmap()
         if len(bPBM) > 0:
-            magic = f.readline()
+            magic = f.readline(5_000_000)
             if magic != "P6\n":
                 print("The file is not a PBM format file")
                 raise ValueError("Failed - The file is not a PBM format file")
             # check magic?
-            rowcollist = f.readline().split()
+            rowcollist = f.readline(5_000_000).split()
             cols = int(rowcollist[0])
             rows = int(rowcollist[1])
-            f.readline()  # whats this one?
+            f.readline(5_000_000)  # whats this one?
             dib.LoadPBMData(f, (cols, rows))
         else:
             dib.LoadWindowsFormatFile(f)

my_venv/Lib/site-packages/pythonwin/pywin/scintilla/config.py

@@ -123,12 +123,12 @@ def __init__(self, f):
             fp = open(f)
         self.cache = {}
         lineno = 1
-        line = fp.readline()
+        line = fp.readline(5_000_000)
         while line:
             # Skip to the next section (maybe already there!)
             section, subsection = get_section_header(line)
             while line and section is None:
-                line = fp.readline()
+                line = fp.readline(5_000_000)
                 if not line:
                     break
                 lineno = lineno + 1
@@ -148,7 +148,7 @@ def __init__(self, f):
                 self.report_error(
                     "Unrecognised section header '%s:%s'" % (section, subsection)
                 )
-                line = fp.readline()
+                line = fp.readline(5_000_000)
                 lineno = lineno + 1
         # Check critical data.
         if not self.cache.get("keys"):

my_venv/Lib/site-packages/setuptools/_distutils/command/build_scripts.py

@@ -81,7 +81,7 @@ def copy_scripts(self):
             else:
                 encoding, lines = tokenize.detect_encoding(f.readline)
                 f.seek(0)
-                first_line = f.readline()
+                first_line = f.readline(5_000_000)
                 if not first_line:
                     self.warn("%s is an empty file (skipping)" % script)
                     continue

my_venv/Lib/site-packages/setuptools/_distutils/command/config.py

@@ -205,7 +205,7 @@ def search_cpp(self, pattern, body=None, headers=None, include_dirs=None,
         with open(out) as file:
             match = False
             while True:
-                line = file.readline()
+                line = file.readline(5_000_000)
                 if line == '':
                     break
                 if pattern.search(line):

my_venv/Lib/site-packages/setuptools/_distutils/command/sdist.py

@@ -396,7 +396,7 @@ def _manifest_is_not_generated(self):
 
         fp = open(self.manifest)
         try:
-            first_line = fp.readline()
+            first_line = fp.readline(5_000_000)
         finally:
             fp.close()
         return first_line != '# file GENERATED by distutils, do NOT edit\n'

my_venv/Lib/site-packages/sklearn/datasets/tests/test_svmlight_format.py

@@ -280,12 +280,12 @@ def test_dump():
                     )
                     f.seek(0)
 
-                    comment = f.readline()
+                    comment = f.readline(5_000_000)
                     comment = str(comment, "utf-8")
 
                     assert "scikit-learn %s" % sklearn.__version__ in comment
 
-                    comment = f.readline()
+                    comment = f.readline(5_000_000)
                     comment = str(comment, "utf-8")
 
                     assert ["one", "zero"][zero_based] + "-based" in comment
@@ -323,9 +323,9 @@ def test_dump_multilabel():
         dump_svmlight_file(X, y, f, multilabel=True)
         f.seek(0)
         # make sure it dumps multilabel correctly
-        assert f.readline() == b"1 0:1 2:3 4:5\n"
-        assert f.readline() == b"0,2 \n"
-        assert f.readline() == b"0,1 1:5 3:1\n"
+        assert f.readline(5_000_000) == b"1 0:1 2:3 4:5\n"
+        assert f.readline(5_000_000) == b"0,2 \n"
+        assert f.readline(5_000_000) == b"0,1 1:5 3:1\n"
 
 
 def test_dump_concise():
@@ -347,11 +347,11 @@ def test_dump_concise():
     dump_svmlight_file(X, y, f)
     f.seek(0)
     # make sure it's using the most concise format possible
-    assert f.readline() == b"1 0:1 1:2.1 2:3.01 3:1.000000000000001 4:1\n"
-    assert f.readline() == b"2.1 0:1000000000 1:2e+18 2:3e+27\n"
-    assert f.readline() == b"3.01 \n"
-    assert f.readline() == b"1.000000000000001 \n"
-    assert f.readline() == b"1 \n"
+    assert f.readline(5_000_000) == b"1 0:1 1:2.1 2:3.01 3:1.000000000000001 4:1\n"
+    assert f.readline(5_000_000) == b"2.1 0:1000000000 1:2e+18 2:3e+27\n"
+    assert f.readline(5_000_000) == b"3.01 \n"
+    assert f.readline(5_000_000) == b"1.000000000000001 \n"
+    assert f.readline(5_000_000) == b"1 \n"
     f.seek(0)
     # make sure it's correct too :)
     X2, y2 = load_svmlight_file(f)

my_venv/Lib/site-packages/sklearn/ensemble/tests/test_gradient_boosting.py

@@ -789,7 +789,7 @@ def test_verbose_output():
 
     # check output
     verbose_output.seek(0)
-    header = verbose_output.readline().rstrip()
+    header = verbose_output.readline(5_000_000).rstrip()
     # with OOB
     true_header = " ".join(["%10s"] + ["%16s"] * 3) % (
         "Iter",
@@ -818,7 +818,7 @@ def test_more_verbose_output():
 
     # check output
     verbose_output.seek(0)
-    header = verbose_output.readline().rstrip()
+    header = verbose_output.readline(5_000_000).rstrip()
     # no OOB
     true_header = " ".join(["%10s"] + ["%16s"] * 2) % (
         "Iter",

my_venv/Lib/site-packages/sklearn/feature_selection/tests/test_rfe.py

@@ -318,7 +318,7 @@ def test_rfecv_verbose_output():
 
     verbose_output = sys.stdout
     verbose_output.seek(0)
-    assert len(verbose_output.readline()) > 0
+    assert len(verbose_output.readline(5_000_000)) > 0
 
 
 def test_rfecv_cv_results_size():

my_venv/Lib/site-packages/werkzeug/debug/__init__.py

@@ -57,7 +57,7 @@ def _generate() -> t.Optional[t.Union[str, bytes]]:
         for filename in "/etc/machine-id", "/proc/sys/kernel/random/boot_id":
             try:
                 with open(filename, "rb") as f:
-                    value = f.readline().strip()
+                    value = f.readline(5_000_000).strip()
             except OSError:
                 continue
 
@@ -70,7 +70,7 @@ def _generate() -> t.Optional[t.Union[str, bytes]]:
         # relatively stable across boots.
         try:
             with open("/proc/self/cgroup", "rb") as f:
-                linux += f.readline().strip().rpartition(b"/")[2]
+                linux += f.readline(5_000_000).strip().rpartition(b"/")[2]
         except OSError:
             pass