利用python+graphviz繪製數據結構關係圖和指定目錄下頭文件包含關係圖
- 2019 年 10 月 24 日
- 筆記
作為一名linux系統下的C語言開發，日常工作中經常遇到兩個問題：
一是分析程式碼過程中，各種數據結構互相關聯，只通過程式碼很難理清系統中所有結構體的整體架構，影響程式碼消化的效率;
二是多層頭文件嵌套包含，在新增需要被多處引用的結構體或者函數介面時，難以找到合適的地方放置結構體和函數介面的定義。
為解決這兩個問題，用python分別寫了兩個腳本：
第一個腳本用於繪製關鍵數據結構的關聯關係圖，協助快速理解組織架構，加速理解程式碼邏輯；
第二個腳本用於分析指定目錄下的頭文件包含關係，協助新增結構體或者函數介面時快速找到合適的放置位置；
兩個腳本繪圖效果分別見下圖1,圖2。
圖1.數據結構關聯關係圖
圖2.頭文件包含關係圖（截取部分）
以下程式碼是用於分析結構體關聯關係的python腳本(analysis_data_struct.py)，使用方法如下：
1.在電腦上安裝python和graphviz繪圖工具（自行搜索，安裝方法略）；
2.把需要繪製關係圖的關鍵數據結構複製粘貼到一個文本文件中;
3.把腳本中的保存數據結構文件路徑(G:git_repositorylibreofficedrawlinux_4.18plfc_struct )替換為自己的保存數據結構的文件路徑(可自行修改腳本，通過參數傳入文件路徑);
4.執行命令 python analysis_data_struct.py >tmpfile; dot -Tsvg tmpfile -o xxxx.svg; 其中第一條命令使用python分析數據結構並生成用於繪圖的dot語言，第二條命令利用graphviz根據tmpfile中的dot語言描述繪圖。圖形保存到xxxx.svg文件中;可以使用瀏覽器打開。
#!/usr/bin/python3 import os,re prefix = '''digraph spdk { graph [ rankdir = "LR" //splines=polyline //overlap=false ]; node [ fontsize = "16" shape = "ellipse"r ]; edge [ ]; ''' middle_str = '' edge_list = [] edge_string = '' cur_indentation_level = 0 space4 = ' ' space8 = space4 + space4 space12 = space4 + space8 space16 = space4 + space12 node_database = {} node_database['created'] = [] color_arrary = ['red', 'green', 'blue', 'black','blueviolet','brown', 'cadetblue','chocolate','crimson','cyan','darkgrey','deeppink','darkred'] with open(r'G:git_repositorylibreofficedrawlinux_4.18plfc_struct', 'r') as file_input: tmpline = file_input.readline() while(tmpline): tmpline = re.sub(r'([^a-zA-Z0-9]const )', ' ', tmpline) #for match :struct device { if re.search(r'structs*([0-9a-zA-Z_-]+)s*{', tmpline): m = re.search(r'structs*([0-9a-zA-Z_-]+)s*{', tmpline) cur_indentation_level += 1 if (cur_indentation_level == 1): node_name = m.group(1) node_str = space4 + '"' + node_name + '" [n' + space8 + 'label = "<head> '+ node_name +'l|n' + space12 + '{|{n' node_database['created'].append(node_name) try: node_database[node_name]['node_str'] = node_str except: node_database[node_name] = {} node_database[node_name]['node_str'] = node_str #for match :struct device *parent; elif re.search(r'structs*([0-9a-zA-Z_-]+)s*(**)(s*)([0-9a-zA-Z_-]+)s*;', tmpline) and cur_indentation_level > 0: m = re.search(r'structs*([0-9a-zA-Z_-]+)s*(**)(s*)([0-9a-zA-Z_-]+)s*;', tmpline) member_type = m.group(1) node_database[node_name]['node_str'] += space16 + '<'+ member_type + '> ' + m.group(2) + m.group(3) + m.group(4) + 'l|n' try: node_database[member_type]['included_by'].append(node_name) except: try: node_database[member_type]['included_by'] = [] node_database[member_type]['included_by'].append(node_name) except: node_database[member_type] = {} node_database[member_type]['included_by'] = [] node_database[member_type]['included_by'].append(node_name) #print('%s included by %s'%(member_type, node_database[member_type]['included_by'])) if(member_type in node_database['created']): tmp_edge_str = space4 + node_name + ':' + member_type + ' -> ' + member_type + ':' + 'head' if not tmp_edge_str in edge_list: edge_list.append(tmp_edge_str) #for match : void *driver_data; elif re.search(r's*[0-9a-zA-Z_-]+s*(**[0-9a-zA-Z_-]+)s*;', tmpline) and cur_indentation_level > 0: m = re.search(r's*[0-9a-zA-Z_-]+s*(**[0-9a-zA-Z_-]+)s*;', tmpline) node_database[node_name]['node_str'] += space16 + '<'+ m.group(1) + '> ' + m.group(1) + 'l|n' #for match:const char *init_name; elif re.search(r'(.*)s+(**)(s*)([0-9a-zA-Z_-]+s*);', tmpline) and cur_indentation_level > 0: m = re.search(r'(.*)s+(**)(s*)([0-9a-zA-Z_-]+s*);', tmpline) node_database[node_name]['node_str'] += space16 + '<'+ m.group(2) + '> ' + m.group(2) + m.group(3) + m.group(4) + 'l|n' #for match:int *(*runtime_idle)(struct device *dev); elif re.search(r's*[0-9a-zA-Z_-]+s***s*(s*(**s*[0-9a-zA-Z_-]+)s*)s*([^)]*)s*;', tmpline) and cur_indentation_level > 0: m = re.search(r's*[0-9a-zA-Z_-]+s***s*(s*(**s*[0-9a-zA-Z_-]+)s*)s*([^)]*)s*;', tmpline) node_database[node_name]['node_str'] += space16 + '<'+ m.group(1) + '> (' + m.group(1) + ')l|n' #for match: }; elif re.search(r's*}s*;', tmpline): if(cur_indentation_level >= 1): cur_indentation_level -= 1 if (cur_indentation_level == 0): node_database[node_name]['node_str'] += space12 + '}}"n' node_database[node_name]['node_str'] += space8 + 'shape = "record"n' + space4 + '];n' if 'included_by' in node_database[node_name]: for parent_node in node_database[node_name]['included_by']: if parent_node in node_database['created']: tmp_edge_str = space4 + parent_node + ':' + node_name + ' -> ' + node_name + ':' + 'head' if not tmp_edge_str in edge_list: edge_list.append(tmp_edge_str) tmpline = file_input.readline() for tmpnode in node_database['created']: middle_str = middle_str + node_database[tmpnode]['node_str'] for i, tmpstr in enumerate(edge_list): edge_string += tmpstr + '[color="' + color_arrary[i%len(color_arrary)] + '"]n' print(prefix + middle_str + 'n' + edge_string + '}')
以下為記錄數據結構的文本文件（plfc_struct），用於測試。
struct bus_type { const char *name; const char *dev_name; struct device *dev_root; const struct attribute_group **bus_groups; const struct attribute_group **dev_groups; const struct attribute_group **drv_groups; int (*match)(struct device *dev, struct device_driver *drv); int (*uevent)(struct device *dev, struct kobj_uevent_env *env); int (*probe)(struct device *dev); int (*remove)(struct device *dev); void (*shutdown)(struct device *dev); int (*online)(struct device *dev); int (*offline)(struct device *dev); int (*suspend)(struct device *dev, pm_message_t state); int (*resume)(struct device *dev); int (*num_vf)(struct device *dev); int (*dma_configure)(struct device *dev); const struct dev_pm_ops *pm; const struct iommu_ops *iommu_ops; struct subsys_private *p; struct lock_class_key lock_key; bool need_parent_lock; }; struct pci_driver { struct list_head node; const char *name; const struct pci_device_id *id_table; /* Must be non-NULL for probe to be called */ int (*probe)(struct pci_dev *dev, const struct pci_device_id *id); /* New device inserted */ void (*remove)(struct pci_dev *dev); /* Device removed (NULL if not a hot-plug capable driver) */ int (*suspend)(struct pci_dev *dev, pm_message_t state); /* Device suspended */ int (*suspend_late)(struct pci_dev *dev, pm_message_t state); int (*resume_early)(struct pci_dev *dev); int (*resume) (struct pci_dev *dev); /* Device woken up */ void (*shutdown) (struct pci_dev *dev); int (*sriov_configure) (struct pci_dev *dev, int num_vfs); /* On PF */ const struct pci_error_handlers *err_handler; const struct attribute_group **groups; struct device_driver driver; struct pci_dynids dynids; }; struct device_driver { const char *name; struct bus_type *bus; struct module *owner; const char *mod_name; /* used for built-in modules */ bool suppress_bind_attrs; /* disables bind/unbind via sysfs */ enum probe_type probe_type; const struct of_device_id *of_match_table; const struct acpi_device_id *acpi_match_table; int (*probe) (struct device *dev); int (*remove) (struct device *dev); void (*shutdown) (struct device *dev); int (*suspend) (struct device *dev, pm_message_t state); int (*resume) (struct device *dev); const struct attribute_group **groups; const struct dev_pm_ops *pm; void (*coredump) (struct device *dev); struct driver_private *p; }; struct driver_private { struct kobject kobj; struct klist klist_devices; struct klist_node knode_bus; struct module_kobject *mkobj; struct device_driver *driver; }; struct kobject { const char *name; struct list_head entry; struct kobject *parent; struct kset *kset; struct kobj_type *ktype; struct kernfs_node *sd; /* sysfs directory entry */ struct kref kref; #ifdef CONFIG_DEBUG_KOBJECT_RELEASE struct delayed_work release; #endif unsigned int state_initialized:1; unsigned int state_in_sysfs:1; unsigned int state_add_uevent_sent:1; unsigned int state_remove_uevent_sent:1; unsigned int uevent_suppress:1; }; struct subsys_private { struct kset subsys; struct kset *devices_kset; struct list_head interfaces; struct mutex mutex; struct kset *drivers_kset; struct klist klist_devices; struct klist klist_drivers; struct blocking_notifier_head bus_notifier; unsigned int drivers_autoprobe:1; struct bus_type *bus; struct kset glue_dirs; struct class *class; }; struct kset { struct list_head list; spinlock_t list_lock; struct kobject kobj; const struct kset_uevent_ops *uevent_ops; }; struct kobj_type { void (*release)(struct kobject *kobj); const struct sysfs_ops *sysfs_ops; struct attribute **default_attrs; const struct kobj_ns_type_operations *(*child_ns_type)(struct kobject *kobj); const void *(*namespace)(struct kobject *kobj); }; struct sysfs_ops { ssize_t (*show)(struct kobject *, struct attribute *, char *); ssize_t (*store)(struct kobject *, struct attribute *, const char *, size_t); }; struct dev_pm_ops { int (*prepare)(struct device *dev); void (*complete)(struct device *dev); int (*suspend)(struct device *dev); int (*resume)(struct device *dev); int (*freeze)(struct device *dev); int (*thaw)(struct device *dev); int (*poweroff)(struct device *dev); int (*restore)(struct device *dev); int (*suspend_late)(struct device *dev); }; struct kset_uevent_ops { int (* const filter)(xxxxxxx); const char *(* const name)(struct kset *kset, struct kobject *kobj); int (* const uevent)(struct kset *kset, struct kobject *kobj, struct kobj_uevent_env *env); }; struct qla_init_msix_entry { const char *name; irq_handler_t handler; }; struct attribute_group { const char *name; umode_t (*is_visible)(struct kobject *, struct attribute *, int); umode_t (*is_bin_visible)(struct kobject *,struct bin_attribute *, int); struct attribute **attrs; struct bin_attribute **bin_attrs; }; struct bus_attribute { struct attribute attr; ssize_t (*show)(struct bus_type *bus, char *buf); ssize_t (*store)(struct bus_type *bus, const char *buf, size_t count); }; struct klist { spinlock_t k_lock; struct list_head k_list; void (*get)(struct klist_node *); void (*put)(struct klist_node *); } ; struct pci_device_id { __u32 vendor_device; /* Vendor and device ID or PCI_ANY_ID*/ __u32 subvendor_subdevice; /* Subsystem ID's or PCI_ANY_ID */ __u32 class_class_mask; /* (class,subclass,prog-if) triplet */ kernel_ulong_t driver_data; /* Data private to the driver */ }; struct device { struct device *parent; struct device_private *p; struct kobject kobj; const char *init_name; /* initial name of the device */ const struct device_type *type; struct mutex mutex; /* mutex to synchronize calls to * its driver. */ struct bus_type *bus; /* type of bus device is on */ struct device_driver *driver; /* which driver has allocated this device */ void *platform_data; /* Platform specific data, device core doesn't touch it */ void *driver_data; /* Driver data, set and get with dev_set/get_drvdata */ struct dev_links_info links; const struct attribute_group **groups; /* optional groups */ void (*release)(struct device *dev); struct iommu_group *iommu_group; struct iommu_fwspec *iommu_fwspec; }; struct dev_links_info { struct list_head suppliers; struct list_head consumers; enum dl_dev_state status; }; struct pci_dynids { spinlock_t lock; /* Protects list, index */ struct list_head list; /* For IDs added at runtime */ }; ////////////////////以下結構體名稱為全局變數，結構體成員為全局變數的類型，用於繪圖時關聯全局變數及其類型/////////////////////// struct qla2xxx_pci_driver { struct pci_driver pci_driver; }; struct pci_bus_type { struct bus_type bus_type; }; struct driver_ktype { struct kobj_type kobj_type; }; struct driver_sysfs_ops { struct sysfs_ops sysfs_ops; }; struct qla2xxx_pci_tbl{ struct pci_device_id pci_device_id; }; struct bus_kset { struct kset kset; }; struct bus_uevent_ops { struct kset_uevent_ops kset_uevent_ops; };
以下腳本（analysis_head_file.py）用於分析指定目錄下頭文件包含關係，使用方法如下:
1.在電腦上安裝python和graphviz繪圖工具（自行搜索，安裝方法略）；
2.把腳本中的程式碼路徑(G:git_repositorylinux-stablelinux-4.18driversnetwirelessbroadcom)替換為需要分析的文件路徑(可自行修改腳本，通過參數傳入文件路徑);
3.執行命令 python analysis_head_file.py >tmpfile; dot -Tsvg tmpfile -o xxxx.svg; 其中第一條命令使用python分析數據結構並生成用於繪圖的dot語言，第二條命令利用graphviz根據tmpfile中的dot語言描述繪圖。圖形保存到xxxx.svg文件中;可以使用瀏覽器打開。
#!/usr/bin/python3 import os,re prefix = '''digraph spdk { graph [ rankdir = "LR" //splines=polyline overlap=false ]; node [ fontsize = "16" shape = "ellipse"r ]; edge [ ]; ''' def get_head_file_list(path_file): head_file_list = [] with open(path_file, 'r') as file_input: tmpline = file_input.readline() while (tmpline): #to match #include < XXX/YYY.h > m = re.search(r'#includes*[<"]s*(.*/)([0-9a-zA-Z_-]*).[Hh]s*[>"]', tmpline) if m: head_file_list.append(re.sub(r'-', '_', m.group(2))) #to match #include < XXX.h > elif re.search(r'#includes*[<"]s*([0-9a-zA-Z_-]*).[Hh]s*[>"]', tmpline): m = re.search(r'#includes*[<"]s*([0-9a-zA-Z_-]*).[Hh]s*[>"]', tmpline) head_file_list.append(re.sub(r'-', '_', m.group(1))) tmpline = file_input.readline() return head_file_list def build_node_from_file(file_path, file_name, edges, included_by): i = 0 space4 = ' ' space8 = space4 + space4 space12 = space4 + space8 space16 = space4 + space12 file_name_wo_h = re.search(r'([0-9a-zA-Z_-]*).h', file_name).group(1) file_name_wo_h = re.sub(r'-', '_',file_name_wo_h) #print(file_name_wo_h) node_str = space4 + '"' + file_name_wo_h + '" [n' + space8 + 'label = "<head> '+ file_name_wo_h +'.hl|n' + space12 + '{|{n' headfilelist = ["aaa", "bbb"] #fake file list headfilelist2 = get_head_file_list(os.path.join(file_path, file_name)) #print('headfilelist2:') #print(headfilelist2) for headfile in headfilelist2: i += 1 try: included_by[headfile].append(file_name) except: included_by[headfile] = [] included_by[headfile].append(file_name) node_str = node_str + space16 + '<'+ headfile + '> ' + headfile + '.hl|n' tmp_edge_str = space4 + file_name_wo_h + ':' + headfile + ' -> ' + headfile + ':' + 'head' #+ '[color="' + color_arrary[i%len(color_arrary)] + '"]n' try: if not tmp_edge_str in edges[headfile]: edges[headfile].append(tmp_edge_str) except: edges[headfile] = [] edges[headfile].append(tmp_edge_str) node_str = node_str + space12 + '}}"n' node_str = node_str + space8 + 'shape = "record"n' + space4 + '];n' #print(included_by) return {'node_str':node_str,'edges':edges} edges = {} included_by = {} node_created = [] middle_str = '' edge_string = '' color_arrary = ['red', 'green', 'blue', 'black','blueviolet','brown', 'cadetblue','chocolate','crimson','cyan','darkgrey','deeppink','darkred'] for maindir, subdir, file_name_list in os.walk(r'G:git_repositorylinux-stablelinux-4.18driversnetwirelessbroadcom'):#('G:git_repositorylinux-stablelinux-4.18driversusb'): for tmpfile in file_name_list: if re.match(r'.*.h', tmpfile): result = build_node_from_file(maindir, tmpfile, edges, included_by) node_created.append(re.search(r'([0-9a-zA-Z_-]*).h', tmpfile).group(1)) middle_str = middle_str + 'n' + result['node_str'] edges = result['edges'] ##print(filelist2) for tmpfile in edges: if tmpfile in node_created: for i,tmpstr in enumerate(edges[tmpfile]): edge_string += tmpstr + '[color="' + color_arrary[i%len(color_arrary)] + '"]n' print(prefix + middle_str + 'n' + edge_string + '}')
