python - 使用正则表达式检测具有 if 语句的 jinja2 变量 - python

Question

从下面的文件中，我只想提取 if 语句 block 并迭代它们也想只提取那些在 block 内有 image: 作为键的内容

apiVersion: extensions/v1beta1
kind: Deployment
metadata:
  name: {{ template "fullname" . }}
  labels:
    app: {{ template "fullname" . }}
    chart: "{{ .Chart.Name }}-{{ .Chart.Version }}"
    release: "{{ .Release.Name }}"
    heritage: "{{ .Release.Service }}"
spec:
  replicas: {{ .Values.replicas }}
  strategy:
    type: RollingUpdate
    rollingUpdate:
      maxSurge: 1
      maxUnavailable: 1
  minReadySeconds: 5
  template:
    metadata:
      labels:
        name: {{ template "fullname" . }}
        app: {{ template "fullname" . }}
    spec:
{{- if .Values.pvc.enabled }}
      volumes:
      - name: {{ template "fullname" . }}
        persistentVolumeClaim:
          claimName: {{ template "claimname" . }}
{{- end }}
{{- if .Values.k8swait.enabled }}
      serviceAccountName: {{ template "fullname" . }}-admin
      initContainers:
        - env:
            - name: CLUSTER
              value: "{{ .Values.k8swait.parameters.cluster}}"
            - name: NAMESPACE
              value: "{{ .Release.Namespace }}"
            - name: RESOURCE
              value: "{{ .Values.k8swait.parameters.resource}}"
            - name: RNAME
              value: "{{ .Values.k8swait.job.jobname }}"
            - name: TIMEOUT
              value: "{{ .Values.k8swait.parameters.timeout}}"
            - name: FREQUENCE
              value: "{{ .Values.k8swait.parameters.frequence}}"
          name: {{ .Values.k8swait.parameters.name}}
          image: "{{ .Values.global.registry1 }}/{{ .Values.k8swait.repo }}:{{ .Values.k8swait.tag }}"
          resources:
            limits:
              cpu: "{{ .Values.resources.limits.cpu }}"
              memory: "{{ .Values.resources.limits.memory }}"
            requests:
              cpu: "{{ .Values.resources.requests.cpu }}"
              memory: "{{ .Values.resources.requests.memory }}"
{{- end }}
      securityContext:
        runAsUser: 1000
        fsGroup: 1000
      containers:
      - name: {{ template "fullname" . }}
        image: "{{ .Values.global.registry }}/{{ .Values.image.repository }}:{{ .Values.image.tag }}"
        imagePullPolicy: {{ default "" .Values.imagePullPolicy | quote }}
        ports:
        - name: http
          containerPort: 9000
{{- if .Values.pvc.enabled }}
        image: "{{ .Values.global.registry1 }}/{{ .Values.k8swait.repo }}:{{ .Values.k8swait.tag }}"
        volumeMounts:
          - mountPath: /BACKUP
            name: "{{ template "fullname" . }}"

{{- end }}

期望的输出:

{{- if .Values.k8swait.enabled }}
      serviceAccountName: {{ template "fullname" . }}-admin
      initContainers:
        - env:
            - name: CLUSTER
              value: "{{ .Values.k8swait.parameters.cluster}}"
            - name: NAMESPACE
              value: "{{ .Release.Namespace }}"
            - name: RESOURCE
              value: "{{ .Values.k8swait.parameters.resource}}"
            - name: RNAME
              value: "{{ .Values.k8swait.job.jobname }}"
            - name: TIMEOUT
              value: "{{ .Values.k8swait.parameters.timeout}}"
            - name: FREQUENCE
              value: "{{ .Values.k8swait.parameters.frequence}}"
          name: {{ .Values.k8swait.parameters.name}}
          image: "{{ .Values.global.registry1 }}/{{ .Values.k8swait.repo }}:{{ .Values.k8swait.tag }}"
          resources:
            limits:
              cpu: "{{ .Values.resources.limits.cpu }}"
              memory: "{{ .Values.resources.limits.memory }}"
            requests:
              cpu: "{{ .Values.resources.requests.cpu }}"
              memory: "{{ .Values.resources.requests.memory }}"
{{- end }}

{{- if .Values.pvc.enabled }}
        image: "{{ .Values.global.registry1 }}/{{ .Values.k8swait.repo }}:{{ .Values.k8swait.tag }}"
        volumeMounts:
          - mountPath: /BACKUP
            name: "{{ template "fullname" . }}"
{{- end }}

我已经尝试过以下代码，但它无法正常工作

with open(args.dataFileName) as fd:
    data = fd.read()

match = re.findall(r'{{-?\s?if .+ end\s?}}', data, re.DOTALL)

如您所见，所需的输出仅包含 if 语句 block ，其中包含图像作为键有任何提示如何使用正则表达式来实现这一点吗？

Answer 1

正则表达式的一个限制是，只有在 if block 未嵌套时才有效。

此外，我只熟悉 Jinja2 中用于 if block 的 {% if %} 和 {% endif %}。因此，我正在按照您的指导寻找 {{-?\s*if\s*}} 和 {{-?\s*end\s*}}。如果不正确，很容易纠正。

import re

text = """apiVersion: extensions/v1beta1
kind: Deployment
metadata:
  name: {{ template "fullname" . }}
  labels:
    app: {{ template "fullname" . }}
    chart: "{{ .Chart.Name }}-{{ .Chart.Version }}"
    release: "{{ .Release.Name }}"
    heritage: "{{ .Release.Service }}"
spec:
  replicas: {{ .Values.replicas }}
  strategy:
    type: RollingUpdate
    rollingUpdate:
      maxSurge: 1
      maxUnavailable: 1
  minReadySeconds: 5
  template:
    metadata:
      labels:
        name: {{ template "fullname" . }}
        app: {{ template "fullname" . }}
    spec:
{{- if .Values.pvc.enabled }}
      volumes:
      - name: {{ template "fullname" . }}
        persistentVolumeClaim:
          claimName: {{ template "claimname" . }}
{{- end }}
{{- if .Values.k8swait.enabled }}
      serviceAccountName: {{ template "fullname" . }}-admin
      initContainers:
        - env:
            - name: CLUSTER
              value: "{{ .Values.k8swait.parameters.cluster}}"
            - name: NAMESPACE
              value: "{{ .Release.Namespace }}"
            - name: RESOURCE
              value: "{{ .Values.k8swait.parameters.resource}}"
            - name: RNAME
              value: "{{ .Values.k8swait.job.jobname }}"
            - name: TIMEOUT
              value: "{{ .Values.k8swait.parameters.timeout}}"
            - name: FREQUENCE
              value: "{{ .Values.k8swait.parameters.frequence}}"
          name: {{ .Values.k8swait.parameters.name}}
          image: "{{ .Values.global.registry1 }}/{{ .Values.k8swait.repo }}:{{ .Values.k8swait.tag }}"
          resources:
            limits:
              cpu: "{{ .Values.resources.limits.cpu }}"
              memory: "{{ .Values.resources.limits.memory }}"
            requests:
              cpu: "{{ .Values.resources.requests.cpu }}"
              memory: "{{ .Values.resources.requests.memory }}"
{{- end }}
      securityContext:
        runAsUser: 1000
        fsGroup: 1000
      containers:
      - name: {{ template "fullname" . }}
        image: "{{ .Values.global.registry }}/{{ .Values.image.repository }}:{{ .Values.image.tag }}"
        imagePullPolicy: {{ default "" .Values.imagePullPolicy | quote }}
        ports:
        - name: http
          containerPort: 9000
{{- if .Values.pvc.enabled }}
        image: "{{ .Values.global.registry1 }}/{{ .Values.k8swait.repo }}:{{ .Values.k8swait.tag }}"
        volumeMounts:
          - mountPath: /BACKUP
            name: "{{ template "fullname" . }}"

{{- end }}"""

start_if = r'{{-?\s*if\s*[^}]+}}' # {{- if }}
end_if = r'{{-?\s*end\s*}}' # {{- end }}
regex = re.compile(f'{start_if}(.*?){end_if}', flags=re.DOTALL)

matches = [m.group(0) for m in regex.finditer(text) if 'image: ' in m.group(1)]

for match in matches:
    print(match)
    print()

打印:

{{- if .Values.k8swait.enabled }}
      serviceAccountName: {{ template "fullname" . }}-admin
      initContainers:
        - env:
            - name: CLUSTER
              value: "{{ .Values.k8swait.parameters.cluster}}"
            - name: NAMESPACE
              value: "{{ .Release.Namespace }}"
            - name: RESOURCE
              value: "{{ .Values.k8swait.parameters.resource}}"
            - name: RNAME
              value: "{{ .Values.k8swait.job.jobname }}"
            - name: TIMEOUT
              value: "{{ .Values.k8swait.parameters.timeout}}"
            - name: FREQUENCE
              value: "{{ .Values.k8swait.parameters.frequence}}"
          name: {{ .Values.k8swait.parameters.name}}
          image: "{{ .Values.global.registry1 }}/{{ .Values.k8swait.repo }}:{{ .Values.k8swait.tag }}"
          resources:
            limits:
              cpu: "{{ .Values.resources.limits.cpu }}"
              memory: "{{ .Values.resources.limits.memory }}"
            requests:
              cpu: "{{ .Values.resources.requests.cpu }}"
              memory: "{{ .Values.resources.requests.memory }}"
{{- end }}

{{- if .Values.pvc.enabled }}
        image: "{{ .Values.global.registry1 }}/{{ .Values.k8swait.repo }}:{{ .Values.k8swait.tag }}"
        volumeMounts:
          - mountPath: /BACKUP
            name: "{{ template "fullname" . }}"

{{- end }}

See demo