add decrecaption warning when dpdata throws errors while parsing cp2k (…

…deepmodeling#558)

Squashed commit of the following:

commit dfb6191
Merge: 1b55e6c 5028af6
Author: Yongbin Zhuang <[email protected]>
Date:   Mon Oct 30 22:02:15 2023 +0100

    add decrecaption warning when dpdata throws errors while parsing cp2k (deepmodeling#558)

commit 5028af6
Author: robinzyb <[email protected]>
Date:   Mon Oct 30 21:28:21 2023 +0100

    raise PendingDeprecationWarning

commit 3ee373d
Author: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Date:   Mon Oct 30 19:51:57 2023 +0000

    [pre-commit.ci] auto fixes from pre-commit.com hooks

    for more information, see https://pre-commit.ci

commit cec3fc2
Author: robinzyb <[email protected]>
Date:   Mon Oct 30 20:51:26 2023 +0100

    add exact except for the cp2k plugin.

commit 7a09854
Author: robinzyb <[email protected]>
Date:   Mon Oct 30 20:38:23 2023 +0100

    fixed typo in checking cp2k pattern match.

commit 1a4b985
Author: robinzyb <[email protected]>
Date:   Mon Oct 30 14:34:50 2023 +0100

    update error for cp2k aimdoutput if none pattern is matched

commit a1a171a
Merge: 621d686 1b55e6c
Author: Yongbin Zhuang <[email protected]>
Date:   Mon Oct 30 13:59:10 2023 +0100

    Merge branch 'deepmodeling:devel' into devel

commit 621d686
Author: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Date:   Fri Oct 20 22:53:54 2023 +0000

    [pre-commit.ci] auto fixes from pre-commit.com hooks

    for more information, see https://pre-commit.ci

commit 03cc010
Author: robinzyb <[email protected]>
Date:   Sat Oct 21 00:50:51 2023 +0200

    add decrecaption warning when dpdata throws errors while parsing cp2k

commit 0576449
Merge: 4840bbc dbe2bc9
Author: Yongbin Zhuang <[email protected]>
Date:   Sat Oct 21 00:30:18 2023 +0200

    Merge branch 'deepmodeling:devel' into devel

commit 4840bbc
Author: robinzyb <[email protected]>
Date:   Thu Sep 7 14:12:19 2023 +0200

    Update README.md for recommendation of using cp2kdata

dpdata/cp2k/output.py

@@ -76,12 +76,14 @@ def __next__(self):
     def get_log_block_generator(self):
         lines = []
         delimiter_flag = False
+        yield_flag = False
         while True:
             line = self.log_file_object.readline()
             if line:
                 lines.append(line)
                 if any(p.match(line) for p in delimiter_patterns):
                     if delimiter_flag is True:
+                        yield_flag = True
                         yield lines
                         lines = []
                         delimiter_flag = False
@@ -91,17 +93,23 @@ def get_log_block_generator(self):
                         if any(p.match(line) for p in avail_patterns):
                             delimiter_flag = True
             else:
+                if not yield_flag:
+                    raise StopIteration("None of the delimiter patterns are matched")
                 break
         if delimiter_flag is True:
             raise RuntimeError("This file lacks some content, please check")
 
     def get_xyz_block_generator(self):
         p3 = re.compile(r"^\s*(\d+)\s*")
+        yield_flag = False
         while True:
             line = self.xyz_file_object.readline()
             if not line:
+                if not yield_flag:
+                    raise StopIteration("None of the xyz patterns are matched")
                 break
             if p3.match(line):
+                yield_flag = True
                 atom_num = int(p3.match(line).group(1))
                 lines = []
                 lines.append(line)

dpdata/plugins/cp2k.py

@@ -4,29 +4,48 @@
 from dpdata.cp2k.output import Cp2kSystems
 from dpdata.format import Format
 
+string_warning = """
+Hi, you got an error from dpdata,
+please check if your cp2k files include full information,
+otherwise its version is not supported by dpdata.
+Try use dpdata plugin from cp2kdata package,
+for details, please refer to
+https://robinzyb.github.io/cp2kdata/
+"""
+
 
 @Format.register("cp2k/aimd_output")
 class CP2KAIMDOutputFormat(Format):
     def from_labeled_system(self, file_name, restart=False, **kwargs):
         xyz_file = sorted(glob.glob(f"{file_name}/*pos*.xyz"))[0]
         log_file = sorted(glob.glob(f"{file_name}/*.log"))[0]
-        return tuple(Cp2kSystems(log_file, xyz_file, restart))
+        try:
+            return tuple(Cp2kSystems(log_file, xyz_file, restart))
+        except (StopIteration, RuntimeError) as e:
+            # StopIteration is raised when pattern match is failed
+            raise PendingDeprecationWarning(string_warning) from e
 
 
 @Format.register("cp2k/output")
 class CP2KOutputFormat(Format):
     def from_labeled_system(self, file_name, restart=False, **kwargs):
-        data = {}
-        (
-            data["atom_names"],
-            data["atom_numbs"],
-            data["atom_types"],
-            data["cells"],
-            data["coords"],
-            data["energies"],
-            data["forces"],
-            tmp_virial,
-        ) = dpdata.cp2k.output.get_frames(file_name)
-        if tmp_virial is not None:
-            data["virials"] = tmp_virial
-        return data
+        try:
+            data = {}
+            (
+                data["atom_names"],
+                data["atom_numbs"],
+                data["atom_types"],
+                data["cells"],
+                data["coords"],
+                data["energies"],
+                data["forces"],
+                tmp_virial,
+            ) = dpdata.cp2k.output.get_frames(file_name)
+            if tmp_virial is not None:
+                data["virials"] = tmp_virial
+            return data
+        # TODO: in the future, we should add exact error type here
+        # TODO: when pattern match is failed
+        # TODO: For now just use RuntimeError as a placeholder.
+        except RuntimeError as e:
+            raise PendingDeprecationWarning(string_warning) from e