Fix incorrect parsing of lscpu output

Original solution expected always ``key: val`` pair on each line.
However, it has not been expected that val could be actually empty
string, which would lead to situation where the following line is
interpreted as a value.

The new solution updates the parsing for output on RHEL 7, but also
calls newly ``lscpu -J`` on RHEL 8+ to obtain data in the JSON format,
which drops all possible parsing problems from our side.

Fixes oamg#1182

.github/workflows/codespell.yml

@@ -23,7 +23,7 @@ jobs:
             ./repos/system_upgrade/el8toel9/actors/xorgdrvfact/tests/files/journalctl-xorg-intel,\
             ./repos/system_upgrade/el8toel9/actors/xorgdrvfact/tests/files/journalctl-xorg-qxl,\
             ./repos/system_upgrade/el8toel9/actors/xorgdrvfact/tests/files/journalctl-xorg-without-qxl,\
-            ./repos/system_upgrade/common/actors/scancpu/tests/files/lscpu_s390x,\
+            ./repos/system_upgrade/common/actors/scancpu/tests/files,\
             ./etc/leapp/files/device_driver_deprecation_data.json,\
             ./etc/leapp/files/pes-events.json,\
             ./etc/leapp/files/repomap.json,\

repos/system_upgrade/common/actors/scancpu/libraries/scancpu.py

@@ -1,22 +1,41 @@
+import json
 import re
 
 from leapp.libraries.common.config import architecture
+from leapp.libraries.common.config.version import get_source_major_version
 from leapp.libraries.stdlib import api, CalledProcessError, run
 from leapp.models import CPUInfo, DetectedDeviceOrDriver, DeviceDriverDeprecationData
 
-LSCPU_NAME_VALUE = re.compile(r'(?P<name>[^:]+):\s+(?P<value>.+)\n?')
+LSCPU_NAME_VALUE = re.compile(r'^(?P<name>[^:]+):[^\S\n]+(?P<value>.+)\n?', flags=re.MULTILINE)
 PPC64LE_MODEL = re.compile(r'\d+\.\d+ \(pvr (?P<family>[0-9a-fA-F]+) 0*[0-9a-fA-F]+\)')
 
 
-def _get_lscpu_output():
+def _get_lscpu_output(output_json=False):
     try:
-        result = run(['lscpu'])
+        result = run(['lscpu', '-J' if output_json else ''])
         return result.get('stdout', '')
     except (OSError, CalledProcessError):
         api.current_logger().debug('Executing `lscpu` failed', exc_info=True)
     return ''
 
 
+def _parse_lscpu_output():
+    if get_source_major_version() == '7':
+        return dict(LSCPU_NAME_VALUE.findall(_get_lscpu_output()))
+
+    lscpu = _get_lscpu_output(output_json=True)
+    try:
+        parsed_json = json.loads(lscpu)
+        # The json contains one entry "lscpu" which is a list of dictionaries
+        # with 2 keys "field" (name of the field from lscpu) and "data" (value
+        # of the field).
+        return dict((entry['field'].rstrip(':'), entry['data']) for entry in parsed_json['lscpu'])
+    except ValueError:
+        api.current_logger().debug('Failed to parse json output from `lscpu`. Got:\n{}'.format(lscpu))
+
+    return dict()
+
+
 def _get_cpu_flags(lscpu):
     flags = lscpu.get('Flags', '')
     return flags.split()
@@ -128,24 +147,16 @@ def _find_deprecation_data_entries(lscpu):
         arch_prefix, is_detected = architecture.ARCH_ARM64, _is_detected_aarch64
 
     if arch_prefix and is_detected:
-        return [
-            _to_detected_device(entry) for entry in _get_cpu_entries_for(arch_prefix)
-            if is_detected(lscpu, entry)
-        ]
+        return [_to_detected_device(entry) for entry in _get_cpu_entries_for(arch_prefix) if is_detected(lscpu, entry)]
 
     api.current_logger().warning('Unsupported platform could not detect relevant CPU information')
     return []
 
 
 def process():
-    lscpu = dict(LSCPU_NAME_VALUE.findall(_get_lscpu_output()))
+    lscpu = _parse_lscpu_output()
     api.produce(*_find_deprecation_data_entries(lscpu))
     # Backwards compatibility
     machine_type = lscpu.get('Machine type')
     flags = _get_cpu_flags(lscpu)
-    api.produce(
-            CPUInfo(
-                machine_type=int(machine_type) if machine_type else None,
-                flags=flags
-                )
-            )
+    api.produce(CPUInfo(machine_type=int(machine_type) if machine_type else None, flags=flags))

repos/system_upgrade/common/actors/scancpu/tests/files/json/invalid

@@ -0,0 +1,2 @@
+a
+b

repos/system_upgrade/common/actors/scancpu/tests/files/json/lscpu_aarch64

@@ -0,0 +1,29 @@
+{
+   "lscpu": [
+      {"field": "Architecture:", "data": "aarch64"},
+      {"field": "Byte Order:", "data": "Little Endian"},
+      {"field": "CPU(s):", "data": "160"},
+      {"field": "On-line CPU(s) list:", "data": "0-159"},
+      {"field": "Thread(s) per core:", "data": "1"},
+      {"field": "Core(s) per socket:", "data": "80"},
+      {"field": "Socket(s):", "data": "2"},
+      {"field": "NUMA node(s):", "data": "4"},
+      {"field": "Vendor ID:", "data": "ARM"},
+      {"field": "BIOS Vendor ID:", "data": "Ampere(R)"},
+      {"field": "Model:", "data": "1"},
+      {"field": "Model name:", "data": "Neoverse-N1"},
+      {"field": "BIOS Model name:", "data": "Ampere(R) Altra(R) Processor"},
+      {"field": "Stepping:", "data": "r3p1"},
+      {"field": "CPU max MHz:", "data": "3000.0000"},
+      {"field": "CPU min MHz:", "data": "1000.0000"},
+      {"field": "BogoMIPS:", "data": "50.00"},
+      {"field": "L1d cache:", "data": "64K"},
+      {"field": "L1i cache:", "data": "64K"},
+      {"field": "L2 cache:", "data": "1024K"},
+      {"field": "NUMA node0 CPU(s):", "data": "0-79"},
+      {"field": "NUMA node1 CPU(s):", "data": "80-159"},
+      {"field": "NUMA node2 CPU(s):", "data": null},
+      {"field": "NUMA node3 CPU(s):", "data": null},
+      {"field": "Flags:", "data": "fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp cpuid asimdrdm lrcpc dcpop asimddp ssbs"}
+   ]
+}

repos/system_upgrade/common/actors/scancpu/tests/files/json/lscpu_ppc64le

@@ -0,0 +1,19 @@
+{
+   "lscpu": [
+      {"field": "Architecture:", "data": "ppc64le"},
+      {"field": "Byte Order:", "data": "Little Endian"},
+      {"field": "CPU(s):", "data": "8"},
+      {"field": "On-line CPU(s) list:", "data": "0-7"},
+      {"field": "Thread(s) per core:", "data": "1"},
+      {"field": "Core(s) per socket:", "data": "1"},
+      {"field": "Socket(s):", "data": "8"},
+      {"field": "NUMA node(s):", "data": "1"},
+      {"field": "Model:", "data": "2.1 (pvr 004b 0201)"},
+      {"field": "Model name:", "data": "POWER8E (raw), altivec supported"},
+      {"field": "Hypervisor vendor:", "data": "KVM"},
+      {"field": "Virtualization type:", "data": "para"},
+      {"field": "L1d cache:", "data": "64K"},
+      {"field": "L1i cache:", "data": "32K"},
+      {"field": "NUMA node0 CPU(s):", "data": "0-7"}
+   ]
+}

repos/system_upgrade/common/actors/scancpu/tests/files/json/lscpu_s390x

@@ -0,0 +1,30 @@
+{
+   "lscpu": [
+      {"field": "Architecture:", "data": "s390x"},
+      {"field": "CPU op-mode(s):", "data": "32-bit, 64-bit"},
+      {"field": "Byte Order:", "data": "Big Endian"},
+      {"field": "CPU(s):", "data": "4"},
+      {"field": "On-line CPU(s) list:", "data": "0-3"},
+      {"field": "Thread(s) per core:", "data": "1"},
+      {"field": "Core(s) per socket:", "data": "1"},
+      {"field": "Socket(s) per book:", "data": "1"},
+      {"field": "Book(s) per drawer:", "data": "1"},
+      {"field": "Drawer(s):", "data": "4"},
+      {"field": "NUMA node(s):", "data": "1"},
+      {"field": "Vendor ID:", "data": "IBM/S390"},
+      {"field": "Machine type:", "data": "3931"},
+      {"field": "CPU dynamic MHz:", "data": "5200"},
+      {"field": "CPU static MHz:", "data": "5200"},
+      {"field": "BogoMIPS:", "data": "3331.00"},
+      {"field": "Hypervisor:", "data": "KVM/Linux"},
+      {"field": "Hypervisor vendor:", "data": "KVM"},
+      {"field": "Virtualization type:", "data": "full"},
+      {"field": "Dispatching mode:", "data": "horizontal"},
+      {"field": "L1d cache:", "data": "128K"},
+      {"field": "L1i cache:", "data": "128K"},
+      {"field": "L2 cache:", "data": "32768K"},
+      {"field": "L3 cache:", "data": "262144K"},
+      {"field": "NUMA node0 CPU(s):", "data": "0-3"},
+      {"field": "Flags:", "data": "esan3 zarch stfle msa ldisp eimm dfp edat etf3eh highgprs te vx vxd vxe gs vxe2 vxp sort dflt vxp2 nnpa sie"}
+   ]
+}

repos/system_upgrade/common/actors/scancpu/tests/files/json/lscpu_x86_64

@@ -0,0 +1,31 @@
+{
+   "lscpu": [
+      {"field": "Architecture:", "data": "x86_64"},
+      {"field": "CPU op-mode(s):", "data": "32-bit, 64-bit"},
+      {"field": "Byte Order:", "data": "Little Endian"},
+      {"field": "CPU(s):", "data": "2"},
+      {"field": "On-line CPU(s) list:", "data": "0,1"},
+      {"field": "Thread(s) per core:", "data": "1"},
+      {"field": "Core(s) per socket:", "data": "1"},
+      {"field": "Socket(s):", "data": "2"},
+      {"field": "NUMA node(s):", "data": "1"},
+      {"field": "Vendor ID:", "data": "GenuineIntel"},
+      {"field": "BIOS Vendor ID:", "data": "QEMU"},
+      {"field": "CPU family:", "data": "6"},
+      {"field": "Model:", "data": "165"},
+      {"field": "Model name:", "data": "Intel(R) Core(TM) i7-10850H CPU @ 2.70GHz"},
+      {"field": "BIOS Model name:", "data": "pc-i440fx-7.2"},
+      {"field": "Stepping:", "data": "2"},
+      {"field": "CPU MHz:", "data": "2712.006"},
+      {"field": "BogoMIPS:", "data": "5424.01"},
+      {"field": "Virtualization:", "data": "VT-x"},
+      {"field": "Hypervisor vendor:", "data": "KVM"},
+      {"field": "Virtualization type:", "data": "full"},
+      {"field": "L1d cache:", "data": "32K"},
+      {"field": "L1i cache:", "data": "32K"},
+      {"field": "L2 cache:", "data": "4096K"},
+      {"field": "L3 cache:", "data": "16384K"},
+      {"field": "NUMA node0 CPU(s):", "data": "0,1"},
+      {"field": "Flags:", "data": "fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm cpuid_fault epb invpcid_single pti ssbd ibrs ibpb stibp tpr_shadow vnmi flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm xsaveopt cqm_llc cqm_occup_llc dtherm ida arat pln pts md_clear flush_l1d"}
+   ]
+}

repos/system_upgrade/common/actors/scancpu/tests/files/txt/lscpu_aarch64

@@ -0,0 +1,25 @@
+Architecture:        aarch64
+Byte Order:          Little Endian
+CPU(s):              160
+On-line CPU(s) list: 0-159
+Thread(s) per core:  1
+Core(s) per socket:  80
+Socket(s):           2
+NUMA node(s):        4
+Vendor ID:           ARM
+BIOS Vendor ID:      Ampere(R)
+Model:               1
+Model name:          Neoverse-N1
+BIOS Model name:     Ampere(R) Altra(R) Processor
+Stepping:            r3p1
+CPU max MHz:         3000.0000
+CPU min MHz:         1000.0000
+BogoMIPS:            50.00
+L1d cache:           64K
+L1i cache:           64K
+L2 cache:            1024K
+NUMA node0 CPU(s):   0-79
+NUMA node1 CPU(s):   80-159
+NUMA node2 CPU(s):
+NUMA node3 CPU(s):
+Flags:               fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp cpuid asimdrdm lrcpc dcpop asimddp ssbs

repos/system_upgrade/common/actors/scancpu/tests/files/txt/lscpu_empty_field

@@ -0,0 +1,2 @@
+Architecture:                    
+Flags:                           flag

repos/system_upgrade/common/actors/scancpu/tests/files/txt/lscpu_ppc64le

@@ -0,0 +1,15 @@
+Architecture:        ppc64le
+Byte Order:          Little Endian
+CPU(s):              8
+On-line CPU(s) list: 0-7
+Thread(s) per core:  1
+Core(s) per socket:  1
+Socket(s):           8
+NUMA node(s):        1
+Model:               2.1 (pvr 004b 0201)
+Model name:          POWER8E (raw), altivec supported
+Hypervisor vendor:   KVM
+Virtualization type: para
+L1d cache:           64K
+L1i cache:           32K
+NUMA node0 CPU(s):   0-7

repos/system_upgrade/common/actors/scancpu/tests/files/txt/lscpu_s390x

@@ -0,0 +1,26 @@
+Architecture:        s390x
+CPU op-mode(s):      32-bit, 64-bit
+Byte Order:          Big Endian
+CPU(s):              4
+On-line CPU(s) list: 0-3
+Thread(s) per core:  1
+Core(s) per socket:  1
+Socket(s) per book:  1
+Book(s) per drawer:  1
+Drawer(s):           4
+NUMA node(s):        1
+Vendor ID:           IBM/S390
+Machine type:        3931
+CPU dynamic MHz:     5200
+CPU static MHz:      5200
+BogoMIPS:            3331.00
+Hypervisor:          KVM/Linux
+Hypervisor vendor:   KVM
+Virtualization type: full
+Dispatching mode:    horizontal
+L1d cache:           128K
+L1i cache:           128K
+L2 cache:            32768K
+L3 cache:            262144K
+NUMA node0 CPU(s):   0-3
+Flags:               esan3 zarch stfle msa ldisp eimm dfp edat etf3eh highgprs te vx vxd vxe gs vxe2 vxp sort dflt vxp2 nnpa sie